Frozen Policy Iteration: Computationally Efficient RL under Linear Qπ Realizability for Deterministic Dynamics

Summarise with VIRAT
Authors: Yijing Ke, Zihan Zhang, Ruosong Wang
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

We study computationally and statistically efficient reinforcement learning under the linear Qπ realizability assumption, where any policy’s Q-function is linear in a given state-action feature representation. Prior methods in this setting are either computationally intractable, or require (local) access to a simulator. In this paper, we propose a computationally efficient online RL algorithm, named Frozen Policy Iteration, under the linear Qπ realizability setting that works for Markov Decision Processes (MDPs) with stochastic initial states, stochastic rewards and deterministic transitions. Our algorithm achieves a regret bound of O(√d2H6T), where d is the dimensionality of the feature space, H is the horizon length, and T is the total number of episodes. Our regret bound is optimal for linear (contextual) bandits which is a special case of our setting with H = 1. Existing policy iteration algorithms under the same setting heavily rely on repeatedly sampling the same state by access to the simulator, which is not implementable in the online setting with stochastic initial states studied in this paper. In contrast, our new algorithm circumvents this limitation by strategically using only high-confidence part of the trajectory data and freezing the policy for well explored states, which ensures that all data used by our algorithm remains effectively on-policy during the whole course of learning. We further demonstrate the versatility of our approach by extending it to the Uniform-PAC setting and to function classes with bounded eluder dimension.

Fields of Study & Subjects

Reinforcement Learning in Robotics Advanced Bandit Algorithms Research Machine Learning and Algorithms

Publication details

Journal / source
Rare & Special e-Zone (The Hong Kong University of Science and Technology)
Publication date
1 January 2026
Language
EN