Exploration methods based on pseudo-count of transitions or curiosity of dynamics have achieved promising results in solving reinforcement learning with sparse rewards. However, such methods are usually sensitive to environmental dynamics-irrelevant information, e.g., white-noise. To handle such dynamics-irrelevant information, we propose a Dynamic Bottleneck (DB) model, which attains a dynamics-relevant representation based on the information-bottleneck principle. Based on the DB model, we further propose DB-bonus, which encourages the agent to explore state-action pairs with high information gain. We establish theoretical connections between the proposed DB-bonus, the upper confidence bound (UCB) for linear case, and the visiting count for tabular case. We evaluate the proposed method on Atari suits with dynamics-irrelevant noises. Our experiments show that exploration with DB bonus outperforms several state-of-the-art exploration methods in noisy environments.
Cite
@article{arxiv.2110.10735,
title = {Dynamic Bottleneck for Robust Self-Supervised Exploration},
author = {Chenjia Bai and Lingxiao Wang and Lei Han and Animesh Garg and Jianye Hao and Peng Liu and Zhaoran Wang},
journal= {arXiv preprint arXiv:2110.10735},
year = {2021}
}