OPIRL: 分布マッチングによるサンプル効率の良いオフポリシー逆強化学習
OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching
オフポリシーデータの分布マッチングを用いて環境との相互作用を大幅に削減し、汎化性の高い報酬関数を学習する逆強化学習手法を提案した論文。
著者: Hana Hoshino, Kei Ota, Asako Kanezaki, Rio Yokota
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Inverse Reinforcement Learning (IRL) is attractive in scenarios where reward engineering can be tedious. However, prior IRL algorithms use on-policy transitions, which require intensive sampling from the current policy for stable and optimal performance. This limits IRL applications in the real world, where environment interactions can become highly expensive. To tackle this problem, we present Off-Policy Inverse Reinforcement Learning (OPIRL), which (1) adopts off-policy data distribution instead of on-policy and enables significant reduction of the number of interactions with the environment, (2) learns a stationary reward function that is transferable with high generalization capabilities on changing dynamics, and (3) leverages mode-covering behavior for faster convergence. We demonstrate that our method is considerably more sample efficient and generalizes to novel environments through the experiments. Our method achieves better or comparable results on policy performance baselines with significantly fewer interactions. Furthermore, we empirically show that the recovered reward function generalizes to different tasks where prior arts are prone to fail.
