Pseudo-visibility: A Game Mechanic Involving Willful Ignorance


  • Samuel Alexander The U.S. Securities and Exchange Commission
  • Arthur Paul Pedersen The City College of New York



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.




How to Cite

Alexander, S., & Pedersen, A. P. (2022). Pseudo-visibility: A Game Mechanic Involving Willful Ignorance. The International FLAIRS Conference Proceedings, 35.



Special Track: Artificial Intelligence in Games, Serious Games, and Multimedia