f-IRL:状態周辺分布マッチングによる逆強化学習
f-IRL: Inverse Reinforcement Learning via State Marginal Matching
エージェントと専門家の状態分布間のfダイバージェンスの解析的勾配を導出し、専門家密度から定常報酬関数を復元するf-IRLを提案。サンプル効率と必要専門家軌跡数で敵対的模倣学習を上回り、下流タスクや動力学変化への行動転移にも有効。
著者: Tianwei Ni, Harshit Sikchi, Yufei Wang, Tejus Gupta, Lisa Lee, Benjamin Eysenbach
分類: cs.LG, cs.RO
原文アブストラクト
Imitation learning is well-suited for robotic tasks where it is difficult to directly program the behavior or specify a cost for optimal control. In this work, we propose a method for learning the reward function (and the corresponding policy) to match the expert state density. Our main result is the analytic gradient of any f-divergence between the agent and expert state distribution w.r.t. reward parameters. Based on the derived gradient, we present an algorithm, f-IRL, that recovers a stationary reward function from the expert density by gradient descent. We show that f-IRL can learn behaviors from a hand-designed target state density or implicitly through expert observations. Our method outperforms adversarial imitation learning methods in terms of sample efficiency and the required number of expert trajectories on IRL benchmarks. Moreover, we show that the recovered reward function can be used to quickly solve downstream tasks, and empirically demonstrate its utility on hard-to-explore tasks and for behavior transfer across changes in dynamics.
