Diversity-Driven Exploration Strategy for Deep Reinforcement Learning

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...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2018-10
Main Authors: Zhang-Wei, Hong, Tzu-Yun Shann, Shih-Yang, Su, Yi-Hsiang, Chang, Chun-Yi, Lee
Format: Article
Language:English
Subjects:
Algorithms
Distance measurement
Exploration
Machine learning
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422