Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Diversity-Driven Exploration Strategy for Deep Reinforcement Learning
Zhang-Wei Hong, Tzu-Yun Shann, Shih-Yang Su, Yi-Hsiang Chang, Chun-Yi Lee
Feb 12, 2018 (modified: Jun 04, 2018)ICLR 2018 Workshop Submissionreaders: everyoneShow Bibtex
Abstract:Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards. To tackle this problem, we present a diversity-driven approach for exploration, which can be easily combined with both off- and on-policy reinforcement learning algorithms. We show that by simply adding a distance measure to the loss function, the proposed methodology significantly enhances an agent's exploratory behaviors, and thus preventing the policy from being trapped in local optima. We further propose an adaptive scaling method for stabilizing the learning process. Our experimental results in Atari 2600 show that our method outperforms baseline approaches in several tasks in terms of mean scores and exploration efficiency.
Keywords:Deep Reinforcement Learning, Exploration
TL;DR:We propose a diversity-driven exploration strategy to improve the exploration efficiency of deep reinforcement learning agents.
Enter your feedback below and we'll get back to you as soon as possible.