RIZE: 模倣学習のための適応的正則化
RIZE: Adaptive Regularization for Imitation Learning
最大エントロピー逆強化学習に適応的な時間差正則化と分布強化学習を組み合わせ、少ない専門家デモでも複雑なタスクで専門家並みの性能を達成する手法を提案。
著者: Adib Karimi, Mohammad Mehdi Ebadzadeh
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
We propose a novel Inverse Reinforcement Learning (IRL) method that mitigates the rigidity of fixed reward structures and the limited flexibility of implicit reward regularization. Building on the Maximum Entropy IRL framework, our approach incorporates a squared temporal-difference (TD) regularizer with adaptive targets that evolve dynamically during training, thereby imposing adaptive bounds on recovered rewards and promoting robust decision-making. To capture richer return information, we integrate distributional RL into the learning process. Empirically, our method achieves expert-level performance on complex MuJoCo and Adroit environments, surpassing baseline methods on the Humanoid-v2 task with limited expert demonstrations. Extensive experiments and ablation studies further validate the effectiveness of the approach and provide insights into reward dynamics in imitation learning. Our source code is available at https://github.com/adibka/RIZE.
