Momentum in Reinforcement Learning

10/21/2019
by   Nino Vieillard, et al.
0

We adapt the optimization's concept of momentum to reinforcement learning. Seeing the state-action value functions as an analog to the gradients in optimization, we interpret momentum as an average of consecutive q-functions. We derive Momentum Value Iteration (MoVI), a variation of Value Iteration that incorporates this momentum idea. Our analysis shows that this allows MoVI to average errors over successive iterations. We show that the proposed approach can be readily extended to deep learning. Specifically, we propose a simple improvement on DQN based on MoVI, and experiment it on Atari games.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset