Pseudo-visibility: A Game Mechanic Involving Willful Ignorance

FLAIRS-35 (2022)
  Copy   BIBTEX

Abstract

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.

Author Profiles

Samuel Allen Alexander
Ohio State University (PhD)
Arthur Paul Pedersen
Carnegie Mellon University (PhD)

Analytics

Added to PP
2022-06-30

Downloads
300 (#49,915)

6 months
123 (#24,486)

Historical graph of downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.
How can I increase my downloads?