On/off-policy Hybrid Deep Reinforcement Learning and Simulation in Control Tasks
-
- WANG Bonan
- University of Tsukuba
-
- KAWAI Shin
- University of Tsukuba
-
- NOBUHARA Hajime
- University of Tsukuba
Bibliographic Information
- Other Title
-
- On/off-policyのハイブリッド深層強化学習とシミュレーション環境での制御問題への応用
Description
<p>Recently, deep reinforcement learning with neural network shows great performance in tasks such as game AI and robotics control tasks. However, on-policy and off-policy reinforcement learning methods proposed in related works have problems such as slow exploration speed. To solve these problems, we propose a hybrid deep reinforcement learning method which combines on-policy and off-policy reinforcement learning in this paper. The comparison experiment shows that the proposed method outperforms classic DDPG and DPPO method with an obvious advantage.</p>
Journal
-
- Proceedings of the Annual Conference of JSAI
-
Proceedings of the Annual Conference of JSAI JSAI2019 (0), 1Q2J205-1Q2J205, 2019
The Japanese Society for Artificial Intelligence
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390845713073510144
-
- NII Article ID
- 130007658327
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- CiNii Articles
-
- Abstract License Flag
- Disallowed