English

Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment

Machine Learning 2024-11-01 v1 Artificial Intelligence

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.

Keywords

Cite

@article{arxiv.2410.23680,
  title  = {Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment},
  author = {Weichao Zhou and Wenchao Li},
  journal= {arXiv preprint arXiv:2410.23680},
  year   = {2024}
}

Comments

arXiv admin note: substantial text overlap with arXiv:2306.01731

R2 v1 2026-06-28T19:42:28.173Z