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)

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)

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.

The AI Robotics Ethics Society (AIRES) is a non-profit organization founded in 2018 by Aaron Hui to promote awareness and the importance of ethical implementation and regulation of AI. AIRES is now an organization with chapters at universities such as UCLA (Los Angeles), USC (University of Southern California), Caltech (California Institute of Technology), Stanford University, Cornell University, Brown University, and the Pontifical Catholic University of Rio Grande do Sul (Brazil). AIRES at PUCRS is the first international chapter of AIRES, and (...) as such, we are committed to promoting and enhancing the AIRES Mission. Our mission is to focus on educating the AI leaders of tomorrow in ethical principles to ensure that AI is created ethically and responsibly. As there are still few proposals for how we should implement ethical principles and normative guidelines in the practice of AI system development, the goal of this work is to try to bridge this gap between discourse and praxis. Between abstract principles and technical implementation. In this work, we seek to introduce the reader to the topic of AI Ethics and Safety. At the same time, we present several tools to help developers of intelligent systems develop "good" models. This work is a developing guide published in English and Portuguese. Contributions and suggestions are welcome. (shrink)

A AI Robotics Ethics Society (AIRES) é uma organização sem fins lucrativos fundada em 2018 por Aaron Hui, com o objetivo de se promover a conscientização e a importância da implementação e regulamentação ética da AI. A AIRES é hoje uma organização com capítulos em universidade como UCLA (Los Angeles), USC (University of Southern California), Caltech (California Institute of Technology), Stanford University, Cornell University, Brown University e a Pontifícia Universidade Católica do Rio Grande do Sul (Brasil). AIRES na PUCRS é (...) o primeiro capítulo internacional da AIRES, e como tal, estamos empenhados em promover e aprimorar a Missão AIRES. Nossa missão é focar na educação dos líderes da IA de amanhã em princípios éticos, para assegurar que a IA seja criada de forma ética e responsável. Como ainda existem poucas propostas de como devemos implementar princípios éticos e diretrizes normativas na prática do desenvolvimento de sistemas de IA, o objetivo deste trabalho é tentar diminuir esta lacuna entre o discurso e a práxis. Entre princípios abstratos e implementação técnica. Neste trabalho, buscamos introduzir o leitor ao tema da Ética e Segurança da IA. Ao mesmo tempo, apresentamos uma série de ferramentas para auxiliar desenvolvedores de sistemas inteligentes a desenvolver “bons” modelos. Este trabalho é um guia em desenvolvimento publicado em inglês e português. Contribuições e sugestões são bem vindas. (shrink)

This is a paper about the general theory of measuring or estimating social intelligence via benchmarks. Hernández-Orallo and Dowe described a problem with certain proposed intelligence measures. The problem suggests that those intelligence measures might not accurately capture social intelligence. We argue that Hernández-Orallo and Dowe's problem is even more general than how they stated it, applying to many subdomains of AGI, not just the one subdomain in which they stated it. We then propose a solution. In our solution, instead (...) of using test-cases within the given AGI subdomain to estimate an AI's intelligence, one would use test-cases in an extended subdomain where test-cases have the ability to simulate the AI being tested. Surprisingly, AIs only designed for the original subdomain can be tested with test-cases in the extended subdomain anyway. By extending the subdomain in this way, we might avoid Hernández-Orallo and Dowe's problem. (shrink)

Choice architecture describes the environment in which choices are presented to decision-makers. In recent years, public and private actors have looked at choice architecture with great interest as they seek to influence human behaviour. These actors are typically called choice architects. Increasingly, however, this role of architecting choice is not performed by a human choice architect, but an algorithm or artificial intelligence, powered by a stream of Big Data and infused with an objective it has been programmed to maximise. We (...) call this entity the autonomous choice architect. In this paper, we present an account of why artificial intelligence can fulfil the role of a choice architect and why this creates problems of transparency, responsibility and accountability for nudges. We argue that choice architects, be them autonomous computational systems or human-beings, at a most basic level select, from a range of designs, the design which is most likely to maximise a pre-determined objective. We then proceed to argue that, given the growing demand for targeted, personalised choice architecture and for faster, dynamic reconfigurations of choice architecture, as well as the ever-expanding pool of data from which feedback can be drawn, the role of the human choice architect is increasingly obscured behind algorithmic, artificially intelligent systems. We provide a discussion of the implications of autonomous choice architects, focusing on the importance of the humans who programme these systems, ultimately arguing that despite technological advances, the responsibility of choice architecture and influence remains firmly one human beings must bear. (shrink)

The fundamental cognitive problem for active organisms is to decide what to do next in a changing environment. In this article, we analyze motor and action control in computational models that utilize reinforcement learning (RL) algorithms. In reinforcement learning, action control is governed by an action selection policy that maximizes the expected future reward in light of a predictive world model. In this paper we argue that RL provides a way to explicate the so-called action-oriented views of cognitive systems in (...) representational terms. (shrink)

Despite the success of artificial intelligence, we are still far away from AI that model the world as humans do. This study focuses for explaining human behavior from intuitive mental models’ perspectives. We describe how behavior arises in biological systems and how the better understanding of this biological system can lead to advances in the development of human-like AI. Human can build intuitive models from physical, social, and cultural situations. In addition, we follow Bayesian inference to combine intuitive models and (...) new information to make decisions. We should build similar intuitive models and Bayesian algorithms for the new AI. We suggest that the probability calculation in Bayesian sense is sensitive to semantic properties of the objects’ combination formed by observation and prior experience. We call this brain process as computational meaningfulness and it is closer to the Bayesian ideal, when the occurrence of probabilities of these objects are believable. How does the human brain form models of the world and apply these models in its behavior? We outline the answers from three perspectives. First, intuitive models support an individual to use information meaningful ways in a current context. Second, neuroeconomics proposes that the valuation network in the brain has essential role in human decision making. It combines psychological, economical, and neuroscientific approaches to reveal the biological mechanisms by which decisions are made. Then, the brain is an over-parameterized modeling organ and produces optimal behavior in a complex word. Finally, a progress in data analysis techniques in AI has allowed us to decipher how the human brain valuates different options in complex situations. By combining big datasets with machine learning models, it is possible to gain insight from complex neural data beyond what was possible before. We describe these solutions by reviewing the current research from this perspective. In this study, we outline the basic aspects for human-like AI and we discuss on how science can benefit from AI. The better we understand human’s brain mechanisms, the better we can apply this understanding for building new AI. Both development of AI and understanding of human behavior go hand in hand. (shrink)

Psychology has benefited from an enormous wealth of knowledge about processes of cognition in relation to how the brain organizes information. Within the categorization literature, this behavior is often explained through theories of memory construction called exemplar theory and prototype theory which are typically based on similarity or rule functions as explanations of how categories emerge. Although these theories work well at modeling highly controlled stimuli in laboratory settings, they often perform less well outside of these settings, such as explaining (...) the emergence of background knowledge processes. In order to explain background knowledge, we present a non-similarity-based post-Skinnerian theory of human language called Relational Frame Theory which is rooted in a philosophical world view called functional contextualism. This theory offers a very different interpretation of how categories emerge through the functions of behavior and through contextual cues, which may be of some benefit to existing categorization theories. Specifically, RFT may be able to offer a novel explanation of how background knowledge arises, and we provide some mathematical considerations in order to identify a formal model. Finally, we discuss much of this work within the broader context of general semantic knowledge and artificial intelligence research. (shrink)

Methods are currently lacking to _prove_ artificial general intelligence (AGI) safety. An AGI ‘hard takeoff’ is possible, in which first generation _AGI 1 _ rapidly triggers a succession of more powerful _AGI n _ that differ dramatically in their computational capabilities (_AGI n _ _n_+1 ). No proof exists that AGI will benefit humans or of a sound value-alignment method. Numerous paths toward human extinction or subjugation have been identified. We suggest that probabilistic proof methods are the fundamental paradigm for (...) proving safety and value-alignment between disparately powerful autonomous agents. Interactive proof systems (IPS) describe mathematical communication protocols wherein a Verifier queries a computationally more powerful Prover and reduces the probability of the Prover deceiving the Verifier to any specified low probability (e.g., 2 −100 ). IPS procedures can test AGI behavior control systems that incorporate hard-coded ethics or value-learning methods. Mapping the axioms and transformation rules of a behavior control system to a finite set of prime numbers allows validation of ‘safe’ behavior via IPS number-theoretic methods. Many other representations are needed for proving various AGI properties. Multi-prover IPS, program-checking IPS, and probabilistically checkable proofs further extend the paradigm. _In toto_, IPS provides a way to reduce _AGI n _ ↔ _AGI_ _n_+1 interaction hazards to an acceptably low level. (shrink)