logo
today local_bar
Poster Session 2 West
Wednesday, December 11, 2024 4:30 PM → 7:30 PM
Poster #6603

Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment

Weichao Zhou, Wenchao Li
Poster

Abstract

Many imitation learning (IL) algorithms use inverse reinforcement learning (IRL) to infer a reward function that aligns with the demonstration.However, the inferred reward functions often fail to capture the underlying task objectives.In this paper, we propose a novel framework for IRL-based IL that prioritizes task alignment over conventional data alignment. Our framework is a semi-supervised approach that leverages expert demonstrations as weak supervision to derive a set of candidate reward functions that align with the task rather than only with the data. It then adopts an adversarial mechanism to train a policy with this set of reward functions to gain a collective validation of the policy's ability to accomplish the task. We provide theoretical insights into this framework's ability to mitigate task-reward misalignment and present a practical implementation. Our experimental results show that our framework outperforms conventional IL baselines in complex and transfer learning scenarios.