部分観測下の強化学習における記憶の分析ツールとPOPGym Arcade
Investigating Memory in Model-Free RL with POPGym Arcade
部分観測環境でエージェントが記憶をどう使うかを分析するツールと、完全観測/部分観測の対照実験が可能なAtari風ベンチマークPOPGym Arcadeを提案し、価値関数が無関係な履歴にクレジットを拡散する問題を明らかにした。
著者: Zekang Wang, Zhe He, Borong Zhang, Edan Toledo, Steven Morad
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
How should we analyze memory in deep RL? We introduce tools for analyzing policies under partial observability and revealing how agents use memory to make decisions. To utilize these tools, we present POPGym Arcade, a collection of Atari-inspired, hardware-accelerated environments sharing a single observation and action space. Each environment provides fully and partially observable variants, enabling counterfactual studies on observability. We find that controlled studies are necessary for fair comparisons and identify a pathology where value functions smear credit over irrelevant history. Using this pathology, we demonstrate how out-of-distribution scenarios can contaminate memory, perturbing the policy far into the future. Our code is available at https://github.com/bolt-research/popgym-arcade.
