Reinforcement Learning (RL) has emerged as a powerful technique for optimizing decision-making in dynamic, uncertain, and complex environments. The ability of RL algorithms to adapt and learn from interactions with the environment enables them to solve challenging problems in fields such as robotics, autonomous systems, finance, and healthcare. In dynamic environments, where conditions change in real-time, RL must continually update its policy to maximize cumulative rewards. This paper explores the application of RL in dynamic environments, with a focus (...) on its ability to optimize real-time decision-making for complex systems. We discuss the challenges associated with these environments, such as non-stationarity, partial observability, and the trade-off between exploration and exploitation. Furthermore, we review recent advancements in RL techniques, including deep reinforcement learning (DRL), multi-agent RL, and model-based RL, and how these methods are addressing the complexity of real-time decision-making. Finally, we present a roadmap for future research, highlighting open questions and potential applications of RL in various industries. (shrink)

In this opinionated review, I draw attention to some of the contributions reinforcement learning can make to questions in the philosophy of mind. In particular, I highlight reinforcement learning's foundational emphasis on the role of reward in agent learning, and canvass two ways in which the framework may advance our understanding of perception and motivation.

Reinforcement Learning (RL) has emerged as a powerful technique for optimizing decision-making in dynamic, uncertain, and complex environments. The ability of RL algorithms to adapt and learn from interactions with the environment enables them to solve challenging problems in fields such as robotics, autonomous systems, finance, and healthcare. In dynamic environments, where conditions change in real-time, RL must continually update its policy to maximize cumulative rewards. This paper explores the application of RL in dynamic environments, with a focus (...) on its ability to optimize real-time decision-making for complex systems. We discuss the challenges associated with these environments, such as non-stationarity, partial observability, and the trade-off between exploration and exploitation. Furthermore, we review recent advancements in RL techniques, including deep reinforcement learning (DRL), multi-agent RL, and model-based RL, and how these methods are addressing the complexity of real-time decision-making. Finally, we present a roadmap for future research, highlighting open questions and potential applications of RL in various industries. (shrink)

In their paper 'Reward is enough', Silver et al conjecture that the creation of sufficiently good reinforcement learning (RL) agents is a path to artificial general intelligence (AGI). We consider one aspect of intelligence Silver et al did not consider in their paper, namely, that aspect of intelligence involved in designing RL agents. If that is within human reach, then it should also be within AGI's reach. This raises the question: is there an RL environment which incentivises RL (...) agents to design RL agents? (shrink)

Multi-agent reinforcement learning (MARL) has gained significant attention due to its applications in complex, interactive environments. Traditional MARL approaches often struggle with scalability and non-stationarity as the number of agents increases. Mean Field Reinforcement Learning (MFRL) provides a scalable alternative by approximating interactions using aggregated statistics. However, existing MFRL models fail to capture causal relationships between agent interactions, leading to suboptimal decision-making. In this work, we introduce Causal Mean Field Multi-Agent Reinforcement Learning (Causal-MFRL), which (...) integrates causal inference techniques into the mean field framework. By leveraging causal graphs and counterfactual reasoning, Causal-MFRL improves policy learning and enhances the interpretability of agent behaviors. We evaluate our approach on standard MARL benchmarks, demonstrating superior performance in efficiency, robustness, and generalization. (shrink)

After generalizing the Archimedean property of real numbers in such a way as to make it adaptable to non-numeric structures, we demonstrate that the real numbers cannot be used to accurately measure non-Archimedean structures. We argue that, since an agent with Artificial General Intelligence (AGI) should have no problem engaging in tasks that inherently involve non-Archimedean rewards, and since traditional reinforcement learning rewards are real numbers, therefore traditional reinforcement learning probably will not lead to AGI. We (...) indicate two possible ways traditional reinforcement learning could be altered to remove this roadblock. (shrink)

We consider an extended notion of reinforcement learning in which the environment can simulate the agent and base its outputs on the agent's hypothetical behavior. Since good performance usually requires paying attention to whatever things the environment's outputs are based on, we argue that for an agent to achieve on-average good performance across many such extended environments, it is necessary for the agent to self-reflect. Thus weighted-average performance over the space of all suitably well-behaved extended environments could be (...) considered a way of measuring how self-reflective an agent is. We give examples of extended environments and introduce a simple transformation which experimentally seems to increase some standard RL agents' performance in a certain type of extended environment. (shrink)

Facial recognition technology has gained immense popularity in recent years due to its applications in security, authentication, and personalized user experiences. Traditional facial recognition systems primarily rely on supervised learning techniques to classify and recognize faces based on labeled datasets. However, reinforcement learning (RL), a machine learning paradigm focused on training models through interactions and feedback from the environment, presents a new approach to enhance the adaptability and performance of facial recognition systems. This paper explores the (...) implementation of facial recognition using reinforcement learning, focusing on the advantages RL offers in terms of continuous learning and real-time adaptation. By utilizing an RL agent to improve the feature extraction and classification process, the proposed method dynamically adapts to changing environmental conditions and new facial data, providing more robust recognition capabilities. This paper provides a comprehensive discussion of the proposed model, its architecture, and experimental results. (shrink)

Background Men with antisocial personality disorder show lifelong abnormalities in adaptive decision making guided by the weighing up of reward and punishment information. Among men with antisocial personality disorder, modifi cation of the behaviour of those with additional diagnoses of psychopathy seems particularly resistant to punishment. Methods We did a case-control functional MRI (fMRI) study in 50 men, of whom 12 were violent off enders with antisocial personality disorder and psychopathy, 20 were violent off enders with antisocial personality disorder but (...) not psychopathy, and 18 were healthy non-off enders. We used fMRI to measure brain activation associated with the representation of punishment or reward information during an event-related probabilistic response-reversal task, assessed with standard general linear-model-based analysis. Findings Offenders with antisocial personality disorder and psychopathy displayed discrete regions of increased activation in the posterior cingulate cortex and anterior insula in response to punished errors during the task reversal phase, and decreased activation to all correct rewarded responses in the superior temporal cortex. This finding was in contrast to results for off enders without psychopathy and healthy non-off enders. Interpretation Punishment prediction error signalling in off enders with antisocial personality disorder and psychopathy was highly atypical. This finding challenges the widely held view that such men are simply characterised by diminished neural sensitivity to punishment. Instead, this fi nding indicates altered organisation of the information processing system responsible for reinforcement learning and appropriate decision making. This difference between violent offenders with antisocial personality disorder with and without psychopathy has implications for the causes of these disorders and for treatment approaches. (shrink)

. In the evolving landscape of healthcare, the efficient processing of biomedical signals is critical for real-time diagnosis and personalized treatment. Conventional cloud-based AI systems for biomedical signal processing face challenges such as high latency, bandwidth consumption, and data privacy concerns. Edge computing, which brings data processing closer to the source, has emerged as a potential solution to these limitations. However, optimizing AI models for edge devices, which often have limited computational resources, remains a challenge. This paper proposes an innovative (...) approach to optimize AI models for biomedical signal processing by leveraging reinforcement learning (RL) techniques within edge computing environments. Reinforcement learning offers the potential to dynamically adapt model parameters based on real-time feedback from the edge devices, optimizing the trade-offs between model accuracy, resource utilization, and processing speed. The proposed system is designed to operate with high efficiency on edge devices, enabling faster signal processing while ensuring energy efficiency and maintaining diagnostic accuracy. A detailed review of existing literature highlights the benefits and challenges of edge computing in biomedical applications, the role of reinforcement learning in dynamic optimization, and the limitations of traditional AI models in constrained environments. The proposed system methodology integrates RL for model optimization, focusing on edge devices' unique constraints in terms of power, memory, and processing capacity. Simulation results demonstrate the improved efficiency and accuracy of biomedical signal processing with optimized AI models in edge computing setups, showing significant improvements in real-time diagnostic applications. (shrink)

In the era of exponential data growth, the efficient migration of data in automotive manufacturing systems is a critical challenge for enterprises. Traditional approaches are often time-intensive and error-prone. This paper proposes an intelligent data transition framework leveraging machine learning algorithms to automate, optimize, and ensure the reliability of data migration processes in automotive manufacturing databases. By integrating supervised learning and reinforcement learning techniques, the framework identifies optimal migration paths, predicts potential bottlenecks, and ensures minimal downtime. (...) Experimental results demonstrate significant improvements in data transfer efficiency and accuracy compared to traditional methods. (shrink)

Integrating machine learning (ML) into network management and orchestration has revolutionized edgebased networking paradigms, where real-time decision-making is critical. Traditional network management approaches often struggle with edge environments' dynamic and resource-constrained nature. By leveraging ML algorithms, networks at the edge can achieve enhanced efficiency, automation, and adaptability in areas such as traffic prediction, resource allocation, and anomaly detection (Wang et al., 2021). Supervised and unsupervised learning techniques facilitate proactive network optimization, reducing latency and improving quality of service (QoS) (...) (Li & Zhang, 2020). Furthermore, reinforcement learning (RL) models enable autonomous network orchestration, allowing edge devices to adapt intelligently to fluctuating workloads and environmental conditions (Patel et al., 2019). However, challenges such as data privacy, computational overhead, and model interpretability remain key concerns in deploying ML-driven network orchestration at the edge (Chen et al., 2022). This paper explores state-of-the-art advancements, key challenges, and future research directions in ML-based edge network management, highlighting its potential to drive the next generation of intelligent, self-optimizing networks. (shrink)

This paper presents a human-computer interaction model with a three layers learning mechanism in a pervasive environment. We begin with a discussion around a number of important issues related to human-computer interaction followed by a description of the architecture for a multi-agent cooperative design system for pervasive computing environment. We present our proposed three- layer HCI model and introduce the group formation algorithm, which is predicated on a dynamic sharing niche technology. Finally, we explore the cooperative reinforcement (...) class='Hi'>learning and fusion algorithms; the paper closes with concluding observations and a summary of the principal work and contributions of this paper. (shrink)

Data normalization is a crucial step in database management systems (DBMS), ensuring consistency, minimizing redundancy, and enhancing query performance. Traditional methods of normalization in supermarket sales databases often demand significant manual effort and domain expertise, making the process time-consuming and prone to errors. This paper introduces an innovative machine learning (ML)-based framework to automate data normalization in supermarket sales databases. The proposed approach utilizes both supervised and unsupervised ML techniques to identify functional dependencies, detect anomalies, and suggest optimal schema (...) transformations. Experiments on supermarket sales datasets show substantial improvements in accuracy, scalability, and processing time compared to traditional approaches. The results emphasize the potential of incorporating ML into database management practices to boost operational efficiency and support better decision-making. (shrink)

The integration of Artificial Intelligence (AI) and Machine Learning (ML) into the research landscape has transforming almost every extending field, including pharmaceutical research. The idea of drug discovery itself is very conventional and has long been criticized for being overly lengthy and expensive, which sometimes may take more than 10 years and billions of dollars to develop a certain drug. AI and ML formulate the future of the drug discovery process by using big data to provide preliminary drug candidates (...) more effectively. This paper overviews the innovations defined by AI and ML in the field of drug discovery, major achievements, techniques, and use cases. Additionally, we explore how AI algorithms can enter biological data, inspect drug-target relations, determine optimal drug design, and potentially recompose famous drugs. This means through using big data with the help of AI in the process of research, previously undisclosed patterns that help in developing effective treatments for patients are found. The paper also addresses the related issues and limitations in applying AI in this domain, namely, data quality issues, the interpretability of AI solutions, and some ethical concerns. Herein, to provide a concrete foundation to the concepts mentioned so far, we discuss the different AI applications and case studies in drug discovery from a survey of the available literature. The article also provides information regarding the methodologies used in AI-enabled drug discovery like deep learning, reinforcement learning, and natural language processing. Moreover, we compare the use of conventional and artificial intelligence methods, while demonstrating what is good and what maybe in both. The results section offers a review and an integration of the most recent objectives and recommendations for subsequent research instruction. Therefore, despite these prohibitive AI and ML forecasts for drug discovery improvement, continuous interaction between computational scientists, biologists, and regulatory authorities is functional to fully unlock this potential. (shrink)

This study aimed to identify the learning and business incubation processes and their impact on developing the performance of business incubators in Gaza Strip, and the study relied on the descriptive analytical approach, and the study population consisted of all employees working in business incubators in Gaza Strip in addition to experts and consultants in incubators where their total number reached (62) individuals, and the researchers used the questionnaire as a main tool to collect data through the comprehensive survey (...) method, where (55) questionnaires were retrieved with a recovery rate of (88.7%). The results of the study showed that there is a high approval of the variables of the study, where the dimension of incubation operations came with a relative weight (84.89%), followed by the learning dimension which got a relative weight (82.50%), while the performance level of the incubators got a relative weight (80.12%) and as the study results showed There is a positive relationship statistically between the two dimensions of learning and business incubation processes and performance development in business incubators, and the linear regression analysis model showed that the main effect in improving the performance of business incubators is "after business incubation operations" while it showed weak effect after learning. The study came out with several recommendations, the most important of which is that business incubators seek to reinforce the learning process and incubation processes for business, and the need to periodically evaluate their performance, and that a more effective mechanism be designed to follow up with companies after the end of the incubation period and monitor the progress of these companies. (shrink)

Are the real numbers rich enough to measure intelligence? We generalize a result of Alexander and Hutter about the so-called Legg-Hutter intelligence measures of reinforcement learning agents. Using the generalized result, we exhibit a paradox: in one particular version of the Legg-Hutter intelligence measure, certain agents all have intelligence 0, even though in a certain sense some of them outperform others. We show that this paradox disappears if we vary the Legg-Hutter intelligence measure to be hyperreal-valued rather than (...) real-valued. (shrink)

We present a game mechanic called pseudo-visibility for games inhabited by non-player characters (NPCs) driven by reinforcement learning (RL). NPCs are incentivized to pretend they cannot see pseudo-visible players: the training environment simulates an NPC to determine how the NPC would act if the pseudo-visible player were invisible, and penalizes the NPC for acting differently. NPCs are thereby trained to selectively ignore pseudo-visible players, except when they judge that the reaction penalty is an acceptable tradeoff (e.g., a guard (...) might accept the penalty in order to protect a treasure because losing the treasure would hurt even more). We describe an RL agent transformation which allows RL agents that would not otherwise do so to perform some limited self-reflection to learn the training environments in question. (shrink)

The results are interpreted in terms of a deficit in initial rule learning and subsequent generalization of these rules to new stimuli. Negative feedback is adequately processed at a neural level but this information is not used to improve behaviour on subsequent trials. As learning is degraded, the process of error detection at the moment of the actual response is diminished. Therefore, the current study demonstrates that disturbed error-monitoring processes play a central role in the often reported (...) class='Hi'>learning deficits in individuals with PP. (shrink)

Curiosity is evident in humans of all sorts from early infancy, and it has also been said to appear in a wide range of other animals, including monkeys, birds, rats, and octopuses. The classical definition of curiosity as an intrinsic desire for knowledge may seem inapplicable to animal curiosity: one might wonder how and indeed whether a rat could have such a fancy desire. Even if rats must learn many things to survive, one might expect their learning must be (...) driven by simpler incentives, such as hunger. One might also wonder what proximal signals could guide animals towards knowledge itself, or how something as abstract as knowledge could ever be a motivational target for an unreflective animal. Taking a cue from recent work in reinforcement learning, I argue that surprise functions as a reward signal for the curious animal, and then show how this amounts to a desire for knowledge gain, where knowledge is conceived of as a cognitive adaptation to reality. This adaptation results in a mental state whose existence depends essentially on the truth of its contents, a factive mental state. Curious creatures benefit from an interaction between the prediction-error correction processes of basic learning and the active surprise-seeking force of their curiosity. This internally adversarial interaction accelerates knowledge gain in ways that are very helpful for agents with the restrictions of biological creatures, in environments with the complexity of our natural world. (shrink)

What is common knowledge? According to the dominant iterative model, a group of people commonly knows that p if and only if they each individually know that p, and they furthermore each know that they each know that p, and so on to infinity. According to the integrative model proposed in this paper, a group commonly knows that p when its members are united in a state of mind of the type whose contents must be true. Epistemic integration within a (...) group is enabled by symmetrical signalling processes such as eye contact. In conversational dyads, symmetrical processing operates on pairs of signals produced by the two sides in a familiar format: speakers generate content for joint attention in main channel communication, and addressees evaluate that content in backchannel communication. Processes of reinforcement learning shape our pairwise signalling, driving the accumulation of common knowledge, both in response to extrinsic reward for coordinated action, and in response to the intrinsic reward of curiosity. Where the iterative model caps the epistemic performance of the group at the level of its weakest member, the integrative model of common knowledge shows how groups working together can outperform their strongest member working alone. (shrink)

I propose that the successes and contributions of reinforcement learning urge us to see the mind in a new light, namely, to recognise that the mind is fundamentally evaluative in nature.

A new trend in deep learning, represented by Mutual Information Neural Estimation (MINE) and Information Noise Contrast Estimation (InfoNCE), is emerging. In this trend, similarity functions and Estimated Mutual Information (EMI) are used as learning and objective functions. Coincidentally, EMI is essentially the same as Semantic Mutual Information (SeMI) proposed by the author 30 years ago. This paper first reviews the evolutionary histories of semantic information measures and learning functions. Then, it briefly introduces the author’s semantic information (...) G theory with the rate-fidelity function R(G) (G denotes SeMI, and R(G) extends R(D)) and its applications to multi-label learning, the maximum Mutual Information (MI) classification, and mixture models. Then it discusses how we should understand the relationship between SeMI and Shannon’s MI, two generalized entropies (fuzzy entropy and coverage entropy), Autoencoders, Gibbs distributions, and partition functions from the perspective of the R(G) function or the G theory. An important conclusion is that mixture models and Restricted Boltzmann Machines converge because SeMI is maximized, and Shannon’s MI is minimized, making information efficiency G/R close to 1. A potential opportunity is to simplify deep learning by using Gaussian channel mixture models for pre-training deep neural networks’ latent layers without considering gradients. It also discusses how the SeMI measure is used as the reward function (reflecting purposiveness) for reinforcement learning. The G theory helps interpret deep learning but is far from enough. Combining semantic information theory and deep learning will accelerate their development. (shrink)

Mathematicians and software developers use the word "function" very differently, and yet, sometimes, things that are in practice implemented using the software developer's "function", are mathematically formalized using the mathematician's "function". This mismatch can lead to inaccurate formalisms. We consider a special case of this meta-problem. Various kinds of agents might, in actual practice, make use of private memory, reading and writing to a memory-bank invisible to the ambient environment. In some sense, we humans do this when we silently subvocalize (...) thoughts about the actions we are taking (at least when the environment we're in is too primitive to probe the contents of our brains). Mathematical function formalizations of agents often ignore this ability. We show that in a general agent-environment framework (of which reinforcement learning is a special case), in a technical sense, such private memories do not enable qualitatively different agent behavior. (shrink)

Inspired by recent progress in multi-agent Reinforcement Learning (RL), in this work we examine the collective intelligent behaviour of theoretical universal agents by introducing a weighted mixture operation. Given a weighted set of agents, their weighted mixture is a new agent whose expected total reward in any environment is the corresponding weighted average of the original agents' expected total rewards in that environment. Thus, if RL agent intelligence is quantified in terms of performance across environments, the weighted mixture's (...) intelligence is the weighted average of the original agents' intelligences. This operation enables various interesting new theorems that shed light on the geometry of RL agent intelligence, namely: results about symmetries, convex agent-sets, and local extrema. We also show that any RL agent intelligence measure based on average performance across environments, subject to certain weak technical conditions, is identical (up to a constant factor) to performance within a single environment dependent on said intelligence measure. (shrink)

In modern, culturally-heterogeneous societies, inefficiency of communication of important moral concepts is often evidenced by asymmetrical moral judgements and hypocritical behaviour, especially in our increasingly compartmentalised social landscapes [Rozuel 2011]. This raises the question of how to present target audiences with some (perhaps novel) moral concept, like an ethical dimension of one’s ecological attitude, in a way which would resonate with them, and be conducive to a coherent moral stance, decreasing action-observer biases. We analyse this problem by introducing a formal (...) moral inconsistency framework. We consider the ways in which the aforementioned problem might be tackled in existing cognitive science of morality (CSM) nativist frameworks, and, secondly, we investigate it from the perspective of moral learning, finally proposing the notion of moral dimensionality of a representation in the context of model-based reinforcement learning, as a useful conceptual tool for studying the problem. (shrink)

Where do values live in thought? A straightforward answer is that we (or our brains) make decisions using explicit value representations which are our values. Recent work applying reinforcement learning to decision-making and planning suggests that more specifically, we may represent both the instrumental expected value of actions as well as the intrinsic reward of outcomes. In this paper, I argue that identifying value with either of these representations is incomplete. For agents such as humans and other animals, (...) there is another place where reward can be located in thought: the division of the space of possibilities or ‘state space’. (shrink)

This paper aims to contribute to the existing literature on normative cognition by providing a lineage explanation of human social norm psychology. This approach builds upon theories of goal-directed behavioral control in the reinforcement learning and control literature, arguing that this form of control defines an important class of intentional normative mental states that are instrumental in nature. I defend the view that great ape capacities for instrumental reasoning and our capacity (or family of capacities) for shared intentionality (...) coadapted to each other and argue that the evolution of this capacity has allowed the representation of social norms and the emergence of our capacity for normative guidance. (shrink)

-/- Reprogramming Society: Aligning Human Learning, Education, and AI with the Universal Law of Balance -/- Introduction -/- Throughout history, human societies have struggled with misinformation, irrational decision-making, and social imbalance. The root cause of these issues lies in the way human minds are programmed from birth. Negative thinking and behavior are not inherent traits but the result of flawed learning systems that fail to align with the universal law of balance in nature. To correct this, a holistic (...) transformation of education, governance, media, and AI is necessary. This essay explores how all human learning follows natural laws, how misinformation disrupts balance, and how a properly designed educational system—supported by AI—can reprogram society toward rational and stable decision-making. -/- The Principle of Learning and the Universal Law of Balance -/- All humans are born with the same fundamental learning mechanisms, guided by feedback and adaptation. Learning is a continuous process of correcting imbalances through experience, much like how natural systems maintain equilibrium. However, when incorrect information, false beliefs, or societal conditioning interfere, they create negative programming that leads to irrational decisions and harmful behaviors. -/- Under the universal law of balance, every thought and action should ideally contribute to stability. When individuals or societies operate outside this balance—due to ignorance or misinformation—they generate problems such as corruption, social injustice, and environmental destruction. Therefore, for humanity to function harmoniously, its learning systems must be structured to filter out falsehoods and reinforce rational thinking based on natural laws. -/- The Role of Education in Correcting Negative Programming -/- Current educational systems fail because they do not integrate the principle of balance. Instead of fostering critical thinking and truth-based decision-making, they often reinforce biases, outdated ideologies, and economic or political agendas. This misalignment perpetuates misinformation, leading to poor governance and societal dysfunction. -/- To correct this, education must be redesigned to follow the universal law of balance. This means: -/- 1. Teaching critical thinking – Students must learn how to evaluate information and recognize misinformation. -/- 2. Eliminating dogma-based teaching – While religious and cultural beliefs can coexist with science, education should be rooted in objective reality. -/- 3. Promoting holistic understanding – Instead of fragmented knowledge, subjects should be interconnected to reflect the natural balance of life. -/- 4. Instilling ethical decision-making – Education should train individuals to make choices that maintain societal equilibrium rather than disrupt it. -/- Governance, Media, and the Spread of Misinformation -/- Education alone is not enough; governance and media must also align with the law of balance. Governments often create policies based on political or economic pressures rather than natural equilibrium, leading to resource mismanagement, social inequality, and environmental crises. Meanwhile, media—whether traditional or digital—plays a crucial role in shaping public perception but often spreads misinformation for profit or control. -/- To fix these issues: -/- Governance must be based on rational, balanced decision-making, using policies that prioritize sustainability and long-term stability over short-term gains. -/- Media should be held accountable for spreading misinformation, ensuring that public discourse is grounded in truth rather than manipulation. -/- The Role of AI In Reprogramming Society -/- Artificial intelligence offers a unique opportunity to accelerate the reprogramming of human minds and societal systems. Unlike human institutions, AI can process vast amounts of data without emotional or ideological bias. If AGI is programmed according to the universal law of balance, it can function as an analytical system that: -/- Filters misinformation from education, governance, and media. -/- Validates the accuracy of knowledge before it influences decision-making. -/- Guides leaders and citizens toward rational, balanced choices. -/- However, for AI to achieve this, it must be designed with a deep understanding of the universal formula. AI developers must either be educated on this principle or integrate it directly into AI training models to ensure that future AGI serves as a force for balance rather than chaos. -/- Conclusion -/- Human society is at a critical juncture where misinformation, flawed education, and unbalanced governance threaten global stability. Since all negative human thinking and behavior stem from negative programming, the solution lies in a complete reformation of education, governance, and media—guided by the universal law of balance. AI, if programmed correctly, can serve as the ultimate tool to reprogram society, ensuring that human learning, decision-making, and leadership align with the natural order. Only through this holistic transformation can humanity achieve true progress and harmony. -/- . (shrink)

The predictive processing literature contains at least two different versions of the framework with different theoretical resources at their disposal. One version appeals to so-called optimistic priors to explain agents’ motivation to act (call this optimistic predictive processing). A more recent version appeals to expected free energy minimization to explain how agents can decide between different action policies (call this preference predictive processing). The difference between the two versions has not been properly appreciated, and they are not sufficiently separated in (...) the literature. They constitute two different theories with strikingly different accounts of motivation and action. By reducing all desire-like constructs to belief-like constructs, optimistic predictive processing entails a substantial revision of standard accounts of motivation and action in philosophy and cognitive science. By contrast, preference predictive processing introduces desire-like constructs that play Humean motivational roles in the explanation of action. In this Humean iteration, predictive processing resembles other prominent computational frameworks implementing a distinction between beliefs and desires, such as reinforcement learning and Bayesian decision theory. Ultimately, predictive processing faces a dilemma between parsimony of mental constructs and completeness of its explanations of agency and the mind. (shrink)

I claim that the significance of comic works to influence our attitudes is limited by the conditions under which we find things funny. I argue that we can only find something funny if we regard it as norm-violating in a way that doesn’t make certain cognitive or pragmatic demands upon us. It is compatible with these conditions that humour reinforces our attitude that something is norm-violating. However, it is not compatible with these conditions that, on the basis of finding it (...) funny, we come to reject some existing attitude. Such a rejection would require that we recognize our attitude as norm-violating in a way that has pragmatic force. Thus if a humorous work reveals the absurdity of something, we can either find it funny and not have our attitudes significantly influenced, or else be significantly influenced but not find it funny. (shrink)

We discuss the evolutionary transition from animals with limited experiencing to animals with unlimited experiencing and basic consciousness. This transition was, we suggest, intimately linked with the evolution of associative learning and with flexible reward systems based on, and modifiable by, learning. During associative learning, new pathways relating stimuli and effects are formed within a highly integrated and continuously active nervous system. We argue that the memory traces left by such new stimulus-effect relations form dynamic, flexible, and (...) varied global sensory states, which we call categorizing sensory states . These CSSs acquired a function: they came to act as internal “evaluators” and led to positive and negative reinforcement of new behavior. They are therefore the simplest, distinct, first-person motivational states that an animal can have. They constitute what we call basic consciousness, and are the hallmark of animals that can experience. Since associative learning has been found in many invertebrate taxa that first appeared during the Cambrian era, we propose that the processes underlying basic consciousness are phylogenetically ancient, and that their emergence may have fueled the Cambrian explosion. (shrink)

In this paper, I examine Reinforcement Learning modelling practice in psychiatry, in the context of alcohol use disorders. I argue that the epistemic roles RL currently plays in the development of psychiatric classification and search for explanations of clinically relevant phenomena are best appreciated in terms of Chang’s account of epistemic iteration, and by distinguishing mechanistic and aetiological modes of computational explanation.

Advances in Artificial Intelligence (AI) have driven the evolution of reasoning in modern AI models, particularly with the development of Large Language Models (LLMs) and their "Think and Answer" paradigm. This paper explores the influence of human reinforcement on AI reasoning and its potential to enhance decision-making through dynamic human interaction. It analyzes the roots of bias and fairness in AI, arguing that these issues often stem from human data and reflect inherent human biases. The paper is structured as (...) follows: first, it frames reasoning as a mechanism for ethical reflection, grounded in dynamic learning and feedback loops; second, it discusses how scaling laws suggest that reinforcement learning (RL) can mitigate biases and promote fairness; third, it examines how RL allows models to view algorithmic bias and fairness as approximation problems. Through an experimental study, the paper demonstrates how AI models, empowered by RL, have successfully identified biases across various domains, including gender and socio-economic contexts, highlighting how reasoning improves algorithmic fairness. Ultimately, this work emphasizes the role of RL in mitigating algorithmic bias and enhancing fairness in AI systems. (shrink)

The Philippine educational system established alternative delivery modes of education, such as the Modified Work and Study Program, to eradicate student dropout incidence. This phenomenological study aims to probe the challenges and explore the coping mechanism of MWSP students in studying mathematics. The study was conducted at a public high school offering the program. Six students were chosen to participate in the study. Focus group discussion was utilized for the data gathering of the study. Results showed that mediocrity of resources (...) and conspicuous learning environment were the leading challenges that MWSP students encounter. Moreover, the coping mechanisms include good classroom management, utilization of concrete examples, time scheduling, steward support, motivational encouragement, and recreational and body relaxation. It is recommended that MWSP mathematics teachers integrate innovative strategies, provide more concrete contextualized examples, intensify the development of learning kits, and reinforce teaching and learning through supplementary materials. (shrink)

Discipline and interest are aspects of parenting that affect children’s behavior and academic performance. This study explores the parents’ disciplinary strategies to promote children’s learning interests. The researchers conducted this study due to society’s issue and observation that elementary pupils have a low interest in learning and manifested inappropriate behaviors inside and outside the classroom. The participants were the ten selected parents with children enrolled in 5th Grade in one of the private Catholic elementary schools in Pagadian City, (...) Philippines. A single case study was utilized. It was found that parents experienced challenges in disciplining their children to promote learning interests due to different kinds of behaviors that the children manifest. The participants identified the following behaviors: Too Much Screen Time in Playing Mobile Games and Being Disrespectful. Despite the challenges they have encountered, they were able to overcome those by implementing positive discipline, offering the problem to God, and effective communication to build good relationships with their children. It is important to be gentle and firm in implementing discipline to promote the learning interest of the pupils. Positive discipline inside the classroom allows the pupils to develop skills of responsibility, resiliency, and proper behavior with the use of positive and negative reinforcements that will motivate them to be interested in learning and excel academically. (shrink)

Rapidly expanding data centers along with networks create a fundamental problem regarding resource allocation efficiency. Standard resource management systems prove unable to adapt dynamically to varying workloads so bandwidth allocation and computing utilization stays inefficient. Developers use recent advancements in artificial intelligence technology to build automatic optimization algorithms that instantly adjust resource distributions. Through the integration of machine learning with deep reinforcement learning systems organizations obtain predictive power to prepare resource distribution ahead of time without endangering operational (...) efficiency. According to Gandhi et al. (2012), both tested methods achieve enhanced energy efficiency while preventing delivery slowness. The study explores how AI addresses data facility network resource optimization by examining key techniques and discovering current trends and future development directions. (shrink)

Context — Children and adults with psychopathic traits and conduct or oppositional defiant disorder demonstrate poor decision making and are impaired in reversal learning. However, the neural basis of this impairment has not previously been investigated. Furthermore, despite high comorbidity of psychopathic traits and attention deficit/hyperactivity disorder, to our knowledge, no research has attempted to distinguish neural correlates of childhood psychopathic traits and attention-deficit/hyperactivity disorder. Objective—To determine the neural regions that underlie the reversal learning impairments in children with (...) psychopathic traits plus conduct or oppositional defiant disorder. Design — Case-control study. Setting — Government clinical research institute. Participants — Forty-two adolescents aged 10 to 17 years: 14 with psychopathic traits and oppositional defiant disorder or conduct disorder, 14 with attention-deficit/hyperactivity disorder only, and 14 healthy controls. Main Outcome Measure — Blood oxygenation level–dependent signal as measured via functional magnetic resonance imaging during a probabilistic reversal task. Results — Children with psychopathic traits showed abnormal responses within the ventromedial prefrontal cortex (Brodmann area 10) during punished reversal errors compared with children wit hattention deficit/hyperactivity disorder and healthy children (P < .05 corrected for multiple comparisons). Conclusions — To our knowledge, this study provides the first evidence of abnormal ventromedial prefrontal cortex responsiveness in children with psychopathic traits and demonstrates this dysfunction was not attributable to comorbid attention-deficit/hyperactivity disorder. These findings suggest that reversal learning impairments in patients with developmental psychopathic traits relate to abnormal processing of reinforcement information. (shrink)

Because culture plays a role in determining the aesthetic merit of a work of art, intrinsically similar works can have different aesthetic merit when assessed in different cultures. This paper argues that a form of aesthetic hedonism is best placed to account for this relativity of aesthetic value. This form of hedonism is based on a functional account of aesthetic pleasure, according to which it motivates and enables mental engagement with artworks, and an account of pleasure-learning, in which it (...) reinforces the appreciation of culture specific ways of engaging with art. (shrink)

Ever since 1988, Vietnam has successfully diversified and multilateralised its relationships, whilst placing a strong degree of focus on integration into the international political economy. This multidirectional foreign policy is designed to contribute to a peaceful international environment and a stable domestic one in order to promote economic growth and build up the aggregate strength of the country. At the same time, it is designed to boost the country’s autonomy, protect its sovereignty and territorial integrity, as well as hedge against (...) potential threats. This multidirectional foreign policy has contributed significantly to the economic reformist agenda, formally initiated at the 1986 Sixth Party Congress, otherwise known as Doi Moi. Additionally, it has boosted Vietnam’s international profile and reversed the diplomatic isolation it faced as the Cold War came to a close. As such, multidirectionalism has become a fundamental aspect of the Doi Moi process. This thesis traces the learning process since multidirectionalism’s inception and argues that this learning process, along with the economic benefits reaped, have evolved into positive memories for the Vietnamese Communist Party. This means multidirectionalism continues to be reinforced and as a result, these memories shape Vietnam’s continued expansion of that policy. Additionally, this thesis also offers a conceptual definition to the term multidirectionalism as well as explores the mechanisms through which Vietnam implements this policy. (shrink)

The objective is to analyse the cultural, social and political conditions of a decisive period of Japan’s modernity known by the slogan of “overcoming modernity” (kindai no chokoku). This slogan is the title of a colloquium, which took place in Tokyo in July 1942, eight months after Pearl Harbour, and associated influential and respected intellectuals. This colloquium and slogan signalled a deep and pervasive cultural, political and societal syndrome, conducive in the case of Japan to fascism and ultra-nationalism. But this (...) syndrome is not an experience unique to Japan. It is observed in every modern society, as a step in ofits past but also present evolution. This syndrome signals therefore an ambiguous and highly dangerous period. It expresses the collective experience of a society at a given moment. This experience conditions its relation to the past, its understanding of theits present situationand also the capacity of individuals and groups to respond to theiris present situation. TBut this collective experience is expressed in metaphysics subjective experience and inter-subjective bond reinforcing a community under intense pressure. In Japan, “oOvercoming modernity” expressed a deep disenchantment with toward modernizsation’s effects and sequels, along with grea deep individual anxiety and collective confusion. The case of Japan provides us with a unique knowledge of a major societal syndrome. The goal is to construct a theory capable of identifying today similar periods of deep political and cultural instability in nations like China, France, Russia and others, with the goal to analyse these cases and evaluate the resulting risks and potential responses. (shrink)

The potential for Large Language Models (LLMs) to attain technological singularity—the point at which artificial intelligence (AI) surpasses human intellect and autonomously improves itself—is a critical concern in AI research. This paper explores the feasibility of current LLMs achieving singularity by examining the philosophical and practical requirements for such a development. We begin with a historical overview of AI and intelligence amplification, tracing the evolution of LLMs from their origins to state-of-the-art models. We then proposes a theoretical framework to assess (...) whether existing LLM technologies could satisfy the conditions for singularity, with a focus on Recursive Self-Improvement (RSI) and autonomous code generation. We integrate key component technologies, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), into our analysis, illustrating how these could enable LLMs to independently enhance their reasoning and problem-solving capabilities. By mapping out a potential singularity model lifecycle and examining the dynamics of exponential growth models, we elucidate the conditions under which LLMs might self-replicate and rapidly escalate their intelligence. We conclude with a discussion of the ethical and safety implications of such developments, underscoring the need for responsible and controlled advancement in AI research to mitigate existential risks. Our work aims to contribute to the ongoing dialogue on the future of AI and the critical importance of proactive measures to ensure its beneficial development. (shrink)

The first decade of this century has seen the nascency of the first mathematical theory of general artificial intelligence. This theory of Universal Artificial Intelligence (UAI) has made significant contributions to many theoretical, philosophical, and practical AI questions. In a series of papers culminating in book (Hutter, 2005), an exciting sound and complete mathematical model for a super intelligent agent (AIXI) has been developed and rigorously analyzed. While nowadays most AI researchers avoid discussing intelligence, the award-winning PhD thesis (Legg, 2008) (...) provided the philosophical embedding and investigated the UAI-based universal measure of rational intelligence, which is formal, objective and non-anthropocentric. Recently, effective approximations of AIXI have been derived and experimentally investigated in JAIR paper (Veness et al. 2011). This practical breakthrough has resulted in some impressive applications, finally muting earlier critique that UAI is only a theory. For the first time, without providing any domain knowledge, the same agent is able to self-adapt to a diverse range of interactive environments. For instance, AIXI is able to learn from scratch to play TicTacToe, Pacman, Kuhn Poker, and other games by trial and error, without even providing the rules of the games. These achievements give new hope that the grand goal of Artificial General Intelligence is not elusive. This article provides an informal overview of UAI in context. It attempts to gently introduce a very theoretical, formal, and mathematical subject, and discusses philosophical and technical ingredients, traits of intelligence, some social questions, and the past and future of UAI. (shrink)

Social norms are commonly understood as rules that dictate which behaviors are appropriate, permissible, or obligatory in different situations for members of a given community. Many researchers have sought to explain the ubiquity of social norms in human life in terms of the psychological mechanisms underlying their acquisition, conformity, and enforcement. Existing theories of the psychology of social norms appeal to a variety of constructs, from prediction-error minimization, to reinforcement learning, to shared intentionality, to domain-specific adaptations for norm (...) acquisition. In this paper, we propose a novel methodological and conceptual framework for the cognitive science of social norms that we call normative pluralism. We begin with an analysis of the explanatory aims of the cognitive science of social norms. From this analysis, we derive a recommendation for a reformed conception of its explanandum: a minimally psychological construct that we call normative regularities. Our central empirical proposal is that the psychological underpinnings of social norms are most likely realized by a heterogeneous set of cognitive, motivational, and ecological mechanisms that vary between norms and between individuals, rather than by a single type of process or distinctive norm system. This pluralistic approach, we suggest, offers a methodologically sound point of departure for a fruitful and rigorous science of social norms. (shrink)

I explain and motivate the shutdown problem: the problem of creating artificial agents that (1) shut down when a shutdown button is pressed, (2) don’t try to prevent or cause the pressing of the shutdown button, and (3) otherwise pursue goals competently. I then propose a solution: train agents to have incomplete preferences. Specifically, I propose that we train agents to lack a preference between every pair of different-length trajectories. I suggest a way to train such agents using reinforcement (...) learning: we give the agent lower reward for repeatedly choosing same-length trajectories. (shrink)

The goal of creating Artificial General Intelligence (AGI) – or in other words of creating Turing machines (modern computers) that can behave in a way that mimics human intelligence – has occupied AI researchers ever since the idea of AI was first proposed. One common theme in these discussions is the thesis that the ability of a machine to conduct convincing dialogues with human beings can serve as at least a sufficient criterion of AGI. We argue that this very ability (...) should be accepted also as a necessary condition of AGI, and we provide a description of the nature of human dialogue in particular and of human language in general against this background. We then argue that it is for mathematical reasons impossible to program a machine in such a way that it could master human dialogue behaviour in its full generality. This is (1) because there are no traditional explicitly designed mathematical models that could be used as a starting point for creating such programs; and (2) because even the sorts of automated models generated by using machine learning, which have been used successfully in areas such as machine translation, cannot be extended to cope with human dialogue. If this is so, then we can conclude that a Turing machine also cannot possess AGI, because it fails to fulfil a necessary condition thereof. At the same time, however, we acknowledge the potential of Turing machines to master dialogue behaviour in highly restricted contexts, where what is called “narrow” AI can still be of considerable utility. (shrink)

In this paper, we model a relational notion of subjectivity by means of two experiments in subjective computing. The goal is to determine to what extent a cognitive and social robot can be regarded to act subjectively. The system was implemented as a reinforcement learning agent with a coaching function. To analyze the robotic agent we used the method of levels of abstraction in order to analyze the agent at four levels of abstraction. At one level the agent (...) is described in mentalistic or subjective language respectively. By mapping this mentalistic to an algorithmic, functional, and relational level, we can show to what extent the agent behaves subjectively as we make use of a relational concept of subjectivity that draws upon the relations that hold between the agent and its environment. According to a relational notion of subjectivity, an agent is supposed to be subjective if it exhibits autonomous relations to itself and others, i.e. the agent is not fully determined by a given input but is able to operate on its input and decide what to do with it. This theoretical notion is confirmed by the technical implementation of self-referentiality and social interaction in that the agent shows improved behavior compared to agents without the ability of subjective computing. On the one hand, a relational concept of subjectivity is confirmed, whereas on the other hand, the technical framework of subjective computing is being theoretically founded. (shrink)

This research paper presents an in-depth analysis of advanced artificial intelligence (AI) algorithms designed to automate data preprocessing in the healthcare sector. The automation of data preprocessing is crucial due to the overwhelming volume, diversity, and complexity of healthcare data, which includes medical records, diagnostic imaging, sensor data from medical devices, genomic data, and other heterogeneous sources. These datasets often exhibit various inconsistencies such as missing values, noise, outliers, and redundant or irrelevant information that necessitate extensive preprocessing before being analyzed (...) by machine learning or statistical models. Traditional data preprocessing methods, which are largely manual and time-consuming, can result in errors that affect the quality of the data and, subsequently, the performance of predictive and diagnostic models. Thus, there is a growing need for intelligent, automated systems that can enhance data quality, streamline the preprocessing pipeline, and reduce the time and effort required by healthcare professionals and data scientists. The study begins by outlining the specific challenges associated with healthcare data, including its high dimensionality, incompleteness, and variability across different data sources and formats. These issues not only complicate the preprocessing stage but also hinder the ability to develop robust models capable of making accurate predictions or diagnoses. The paper then explores how AI algorithms—particularly those based on machine learning (ML), deep learning (DL), and reinforcement learning (RL)—can automate key data preprocessing tasks such as data cleaning, feature selection, normalization, and transformation. These algorithms are designed to identify patterns in data, detect anomalies, and automatically apply corrections or transformations based on predefined rules or learned behaviors, thereby minimizing human intervention. The paper also delves into specific AI techniques that have been successfully applied to healthcare data preprocessing. For instance, supervised learning models, such as decision trees and support vector machines (SVMs), have been utilized to perform imputation of missing data by predicting the most likely values based on the available information. Similarly, unsupervised learning methods, such as clustering algorithms, have been employed to group similar data points and remove outliers that could distort the performance of analytical models. Moreover, deep learning techniques, particularly autoencoders and generative adversarial networks (GANs), have demonstrated remarkable effectiveness in transforming high-dimensional medical data into lower-dimensional representations, enabling more efficient and accurate model training. In addition to the discussion of these algorithms, the paper emphasizes the role of natural language processing (NLP) in automating the preprocessing of unstructured healthcare data, such as clinical notes and diagnostic reports. NLP techniques, including named entity recognition (NER) and word embeddings, are instrumental in extracting relevant information from unstructured text, standardizing terminologies, and converting textual data into structured formats suitable for downstream analysis. Furthermore, AI-based feature selection algorithms are explored, which aim to identify the most relevant features in the dataset, thereby reducing its dimensionality and improving the computational efficiency of predictive models. The study goes on to highlight the significant reduction in processing time achieved by AIdriven automation of preprocessing tasks. In conventional settings, data preprocessing accounts for a substantial portion of the time spent on building healthcare models, often requiring expert intervention to manually inspect and clean the data. By employing AI algorithms, not only can this process be expedited, but the accuracy of the resulting data is also enhanced, which translates into better model performance. The paper provides a detailed comparative analysis of manual preprocessing methods versus automated AI-driven approaches, demonstrating the substantial time savings and improvements in data quality brought about by automation. (shrink)

What is cognition? Equivalently, what is cognition good for? Or, what is it that would not be but for human cognition? But for human cognition, there would not be science. Based on this kinship between individual cognition and collective science, here we put forward Isbell conjugacy---the adjointness between objective geometry and subjective algebra---as a scientific method for developing cognitive science. We begin with the correspondence between categorical perception and category theory. Next, we show how the Gestalt maxim is subsumed by (...) the mathematical construct of colimit, a generalization of summation. The universal mapping property definitions of mathematical constructs, by virtue of being the best with respect to the universe of discourse, can be learned using reinforcement learning algorithms, which raises the possibility of abstracting the architecture of mathematics by artificial intelligence. Subsequently, we present naturality (to be contrasted with miracles), understood as 'Becoming consistent with Being', which governs the transformations of both things and their theories, as the zeroth law of change. Furthermore, the contrast---physical [mechanism] vs. biological [organism]---is smoothed via natural transformation, wherein transformations are respectful of the cohesion of the objects transformed. In closing, upon recognizing the scientific value of learning difficult-to-master differential calculus by physicists, of learning a strange four-letter language by biologists, and of learning the grammar of our respective mother tongues, we make a case for learning the theory of naturality / category theory for developing cognitive science. (shrink)