Bayesian Q-learning With Imperfect Expert Demonstrations
Machine Learning
2022-10-06 v1 Artificial Intelligence
Abstract
Guided exploration with expert demonstrations improves data efficiency for reinforcement learning, but current algorithms often overuse expert information. We propose a novel algorithm to speed up Q-learning with the help of a limited amount of imperfect expert demonstrations. The algorithm avoids excessive reliance on expert data by relaxing the optimal expert assumption and gradually reducing the usage of uninformative expert data. Experimentally, we evaluate our approach on a sparse-reward chain environment and six more complicated Atari games with delayed rewards. With the proposed methods, we can achieve better results than Deep Q-learning from Demonstrations (Hester et al., 2017) in most environments.
Cite
@article{arxiv.2210.01800,
title = {Bayesian Q-learning With Imperfect Expert Demonstrations},
author = {Fengdi Che and Xiru Zhu and Doina Precup and David Meger and Gregory Dudek},
journal= {arXiv preprint arXiv:2210.01800},
year = {2022}
}