Dynamic Bottleneck for Robust Self-Supervised Exploration

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.

Authors

• Chenjia Bai Institute of Artificial Intelligence (TeleAI), China Telecom ShenZhen Research Institute of Northwestern Polytechnical University
• Lingxiao Wang
• Lei Han Tencent Robotics X
• Animesh Garg
• Jianye Hao Tianjin University
• Peng Liu
• Zhaoran Wang

Keywords

No keywords are indexed for this paper.