Reward-Based Exploration: Adaptive Control for Deep Reinforcement Learning

Zhi-xiong XU  Lei CAO  Xi-liang CHEN  Chen-xi LI  

IEICE TRANSACTIONS on Information and Systems   Vol.E101-D   No.9   pp.2409-2412
Publication Date: 2018/09/01
Publicized: 2018/06/18
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2018EDL8011
Type of Manuscript: LETTER
Category: Artificial Intelligence, Data Mining
deep reinforcement learning,  reward,  exploration,  exploitation,  

Full Text: PDF(479.2KB)>>
Buy this Article

Aiming at the contradiction between exploration and exploitation in deep reinforcement learning, this paper proposes “reward-based exploration strategy combined with Softmax action selection” (RBE-Softmax) as a dynamic exploration strategy to guide the agent to learn. The superiority of the proposed method is that the characteristic of agent's learning process is utilized to adapt exploration parameters online, and the agent is able to select potential optimal action more effectively. The proposed method is evaluated in discrete and continuous control tasks on OpenAI Gym, and the empirical evaluation results show that RBE-Softmax method leads to statistically-significant improvement in the performance of deep reinforcement learning algorithms.