## Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement Learning

### Yunhao Tang

##### Hall E #829

Keywords: [ RL: Policy Search ] [ MISC: Transfer, Multitask and Meta-learning ] [ Reinforcement Learning ]

[ Abstract ]
[
Wed 20 Jul 3:30 p.m. PDT — 5:30 p.m. PDT

Spotlight presentation: Reinforcement Learning
Wed 20 Jul 10:15 a.m. PDT — 11:45 a.m. PDT

Abstract: Despite the empirical success of meta reinforcement learning (meta-RL), there are still a number poorly-understood discrepancies between theory and practice. Critically, biased gradient estimates are almost always implemented in practice, whereas prior theory on meta-RL only establishes convergence under unbiased gradient estimates. In this work, we investigate such a discrepancy. In particular, (1) We show that unbiased gradient estimates have variance $\Theta(N)$ which linearly depends on the sample size $N$ of the inner loop updates; (2) We propose linearized score function (LSF) gradient estimates, which have bias $\mathcal{O}(1/\sqrt{N})$ and variance $\mathcal{O}(1/N)$; (3) We show that most empirical prior work in fact implements variants of the LSF gradient estimates. This implies that practical algorithms "accidentally" introduce bias to achieve better performance; (4) We establish theoretical guarantees for the LSF gradient estimates in meta-RL regarding its convergence to stationary points, showing better dependency on $N$ than prior work when $N$ is large.

Chat is not available.