自動運転における相反する環境での強化学習
Reinforcement Learning in Conflicting Environments for Autonomous Vehicles
ニューコム問題と囚人のジレンマを題材に、強化学習エージェントが人間との意思決定ジレンマでどう振る舞うかを実験的に調べた論文。
著者: Dominik Meyer, Johannes Feldmaier, Hao Shen
分類: cs.AI, cs.HC, cs.RO
原文アブストラクト
In this work, we investigate the application of Reinforcement Learning to two well known decision dilemmas, namely Newcomb's Problem and Prisoner's Dilemma. These problems are exemplary for dilemmas that autonomous agents are faced with when interacting with humans. Furthermore, we argue that a Newcomb-like formulation is more adequate in the human-machine interaction case and demonstrate empirically that the unmodified Reinforcement Learning algorithms end up with the well known maximum expected utility solution.
