Correcting Momentum in Temporal Difference Learning

7 Jun 2021  ·  Emmanuel Bengio, Joelle Pineau, Doina Precup ·

A common optimization tool used in deep reinforcement learning is momentum, which consists in accumulating and discounting past gradients, reapplying them at each iteration. We argue that, unlike in supervised learning, momentum in Temporal Difference (TD) learning accumulates gradients that become doubly stale: not only does the gradient of the loss change due to parameter updates, the loss itself changes due to bootstrapping. We first show that this phenomenon exists, and then propose a first-order correction term to momentum. We show that this correction term improves sample efficiency in policy evaluation by correcting target value drift. An important insight of this work is that deep RL methods are not always best served by directly importing techniques from the supervised setting.

PDF Abstract


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here