Bayesian Q-learning With Imperfect Expert Demonstrations

1 Oct 2022  ·  Fengdi Che, Xiru Zhu, Doina Precup, David Meger, Gregory Dudek ·

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.

PDF Abstract


  Add Datasets introduced or used in this paper

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.