English

A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations

Machine Learning 2025-02-28 v1

Abstract

This paper investigates how to incorporate expert observations (without explicit information on expert actions) into a deep reinforcement learning setting to improve sample efficiency. First, we formulate an augmented policy loss combining a maximum entropy reinforcement learning objective with a behavioral cloning loss that leverages a forward dynamics model. Then, we propose an algorithm that automatically adjusts the weights of each component in the augmented loss function. Experiments on a variety of continuous control tasks demonstrate that the proposed algorithm outperforms various benchmarks by effectively utilizing available expert observations.

Keywords

Cite

@article{arxiv.2402.18836,
  title  = {A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations},
  author = {Erhan Can Ozcan and Vittorio Giammarino and James Queeney and Ioannis Ch. Paschalidis},
  journal= {arXiv preprint arXiv:2402.18836},
  year   = {2025}
}
R2 v1 2026-06-28T15:04:04.214Z