Timezone: »

 
Poster
Near Optimal Policy Optimization via REPS
Aldo Pacchiano · Jonathan N Lee · Peter Bartlett · Ofir Nachum

Fri Dec 10 08:30 AM -- 10:00 AM (PST) @
in Poster Session 8 »

Since its introduction a decade ago, relative entropy policy search (REPS) has demonstrated successful policy learning on a number of simulated and real-world robotic domains, not to mention providing algorithmic components used by many recently proposed reinforcement learning (RL) algorithms. While REPS is commonly known in the community, there exist no guarantees on its performance when using stochastic and gradient-based solvers. In this paper we aim to fill this gap by providing guarantees and convergence rates for the sub-optimality of a policy learned using first-order optimization methods applied to the REPS objective. We first consider the setting in which we are given access to exact gradients and demonstrate how near-optimality of the objective translates to near-optimality of the policy. We then consider the practical setting of stochastic gradients, and introduce a technique that uses generative access to the underlying Markov decision process to compute parameter updates that maintain favorable convergence to the optimal regularized policy.

Keywords: Optimization · Reinforcement Learning and Planning

Author Information

Aldo Pacchiano (Microsoft Research)
Jonathan N Lee (Stanford University)
Peter Bartlett (UC Berkeley)
Ofir Nachum (Google Brain)

More from the Same Authors