Inverse Delayed Reinforcement Learning
This addresses imitation learning challenges in robotics or control systems where delays occur, but it appears incremental as it builds on existing IRL frameworks.
The paper tackles the problem of extracting rewarding features from expert trajectories affected by delayed disturbances in Inverse Reinforcement Learning, and shows that recovering expert policies from augmented delayed observations outperforms using direct delayed observations, with empirical validation in MuJoCo environments.
Inverse Reinforcement Learning (IRL) has demonstrated effectiveness in a variety of imitation tasks. In this paper, we introduce an IRL framework designed to extract rewarding features from expert trajectories affected by delayed disturbances. Instead of relying on direct observations, our approach employs an efficient off-policy adversarial training framework to derive expert features and recover optimal policies from augmented delayed observations. Empirical evaluations in the MuJoCo environment under diverse delay settings validate the effectiveness of our method. Furthermore, we provide a theoretical analysis showing that recovering expert policies from augmented delayed observations outperforms using direct delayed observations.