Abstract | ||
---|---|---|
Exploration based on state novelty has brought great success in challenging reinforcement learning problems with sparse rewards. However, existing novelty-based strategies become inefficient in real-world problems where observation contains not only task-dependent state novelty of our interest but also task-irrelevant information that should be ignored. We introduce an information- theoretic exploration strategy named Curiosity-Bottleneck that distills task-relevant information from observation. Based on the information bottleneck principle, our exploration bonus is quantified as the compressiveness of observation with respect to the learned representation of a compressive value network. With extensive experiments on static image classification, grid-world and three hard-exploration Atari games, we show that Curiosity-Bottleneck learns an effective exploration strategy by robustly measuring the state novelty in distractive environments where state-of-the-art exploration methods often degenerate. |
Year | Venue | Field |
---|---|---|
2019 | international conference on machine learning | Bottleneck,Curiosity,Computer science,Human–computer interaction,Artificial intelligence,Novelty,Machine learning |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Youngjin Kim | 1 | 19 | 5.12 |
Daniel Nam | 2 | 0 | 0.34 |
Hyun-Woo Kim | 3 | 21 | 6.72 |
Ji-Hoon Kim | 4 | 68 | 10.13 |
Gunhee Kim | 5 | 632 | 47.17 |