Learning to Run with Actor-Critic Ensemble

Preprint English OPEN
Huang, Zhewei; Zhou, Shuchang; Zhuang, BoEr; Zhou, Xinyu;
(2017)
  • Subject: Computer Science - Learning

We introduce an Actor-Critic Ensemble(ACE) method for improving the performance of Deep Deterministic Policy Gradient(DDPG) algorithm. At inference time, our method uses a critic ensemble to select the best action from proposals of multiple actors running in parallel. B... View more
Share - Bookmark