1. Uncertainty Quantification and Exploration for Reinforcement Learning.
- Author
-
Zhu, Yi, Dong, Jing, and Lam, Henry
- Subjects
REINFORCEMENT learning ,CENTRAL limit theorem ,CONFIDENCE regions (Mathematics) ,ASYMPTOTIC distribution ,INFERENTIAL statistics - Abstract
Quantify the uncertainty to decide and explore better In statistical inference, large-sample behavior and confidence interval construction are fundamental in assessing the error and reliability of estimated quantities with respect to the data noises. In the paper "Uncertainty Quantification and Exploration for Reinforcement Learning", Dong, Lam, and Zhu study the large sample behavior in the classic setting of reinforcement learning. They derive appropriate large-sample asymptotic distributions for the state-action value function (Q-value) and optimal value function estimations when data are collected from the underlying Markov chain. This allows one to evaluate the assertiveness of performances among different decisions. The tight uncertainty quantification also facilitates the development of a pure exploration policy by maximizing the worst-case relative discrepancy among the estimated Q-values (ratio of the mean squared difference to the variance). This exploration policy aims to collect informative training data to maximize the probability of learning the optimal reward collecting policy, and it achieves good empirical performance. We investigate statistical uncertainty quantification for reinforcement learning (RL) and its implications in exploration policy. Despite ever-growing literature on RL applications, fundamental questions about inference and error quantification, such as large-sample behaviors, appear to remain quite open. In this paper, we fill in the literature gap by studying the central limit theorem behaviors of estimated Q-values and value functions under various RL settings. In particular, we explicitly identify closed-form expressions of the asymptotic variances, which allow us to efficiently construct asymptotically valid confidence regions for key RL quantities. Furthermore, we utilize these asymptotic expressions to design an effective exploration strategy, which we call Q-value-based Optimal Computing Budget Allocation (Q-OCBA). The policy relies on maximizing the relative discrepancies among the Q-value estimates. Numerical experiments show superior performances of our exploration strategy than other benchmark policies. Funding: This work was supported by the National Science Foundation (1720433). [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF