papers AI Learner
The Github is limit! Click to go to the new site.

Deep Residual Reinforcement Learning

2019-05-03
Shangtong Zhang, Wendelin Boehmer, Shimon Whiteson

Abstract

We revisit residual algorithms in both model-free and model-based reinforcement learning settings. We propose the bidirectional target network technique to stabilize residual algorithms, yielding a residual version of DDPG that significantly outperforms vanilla DDPG in the DeepMind Control Suite benchmark. Moreover, we find the residual algorithm an effective approach to the distribution mismatch problem in model-based planning. Compared with the existing TD($k$) method, our residual-based method makes weaker assumptions about the model and yields a greater performance boost.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.01072

PDF

http://arxiv.org/pdf/1905.01072


Similar Posts

Comments