[1Q2-J-2] Machine learning: reinforcement learning and its advances

[1Q2-J-2-05] On/off-policy Hybrid Deep Reinforcement Learning and Simulation in Control Tasks

〇Bonan Wang¹, Shin Kawai¹, Hajime Nobuhara¹ (1. University of Tsukuba)

Keywords:Reinforcement Learning, Deep Learning, Hybrid, LSTM

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.