Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space
Open access
Date
2023Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
We consider the reinforcement learning (RL) problem with general utilities which consists in maximizing a function of the state-action occupancy measure. Beyond the standard cumulative reward RL setting, this problem includes as particular cases constrained RL, pure exploration and learning from demonstrations among others. For this problem, we propose a simpler single-loop parameter-free normalized policy gradient algorithm. Implementing a recursive momentum variance reduction mechanism, our algorithm achieves $\tilde{O}(\epsilon^{-3})$ and $\tilde{O}(\epsilon^{-2})$ sample complexities for $\epsilon$-first-order stationarity and $\epsilon$-global optimality respectively, under adequate assumptions. We further address the setting of large finite state action spaces via linear function approximation of the occupancy measure and show a $\tilde{O}(\epsilon^{-4})$ sample complexity for a simple policy gradient method with a linear regression subroutine. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000638297Publication status
publishedExternal links
Editor
Book title
Proceedings of the 40th International Conference on Machine LearningJournal / series
Proceedings of Machine Learning ResearchVolume
Pages / Article No.
Publisher
PMLREvent
Subject
reinforcement learning; policy gradient methods; convex RL; Global convergenceOrganisational unit
09729 - He, Niao / He, Niao
02219 - ETH AI Center / ETH AI Center
More
Show all metadata
ETH Bibliography
yes
Altmetrics