A Provably Efficient Model-free Posterior Sampling Method For Episodic Reinforcement Learning

Abstract

Thompson Sampling is one of the most effective methods for contextual bandits and has been generalized to posterior sampling for certain MDP settings. However, existing posterior sampling methods for reinforcement learning are limited by being model-based or lack worst-case theoretical guarantees beyond linear MDPs. This paper proposes a new model-free formulation of posterior sampling that applies to more general episodic reinforcement learning problems with theoretical guarantees. We introduce novel proof techniques to show that under suitable conditions, the worst-case regret of our posterior sampling method matches the best known results of optimization based methods. In the linear MDP setting with dimension, the regret of our algorithm scales linearly with the dimension as compared to a quadratic dependence of the existing posterior sampling-based exploration algorithms.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydann2022a

Related papers

• More Efficient Randomized Exploration For Reinforcement Learning Via Approximate Sampling (2024)0.00
• Provably Efficient Exploration In Constrained Reinforcement Learning:posterior Sampling Is All You Need (2023)0.00
• Posterior Sampling-based Online Learning For Episodic Pomdps (2023)0.00
• Deep Bayesian Bandits Showdown: An Empirical Comparison Of Bayesian Deep Networks For Thompson Sampling (2018)0.00
• Posterior Sampling For Reinforcement Learning: Worst-case Regret Bounds (2017)0.00
• Langevin Thompson Sampling With Logarithmic Communication: Bandits And Reinforcement Learning (2023)0.00
• BOTS: Batch Bayesian Optimization Of Extended Thompson Sampling For Severely Episode-limited RL Settings (2024)0.00
• Optimistic Posterior Sampling For Reinforcement Learning With Few Samples And Tight Guarantees (2022)0.00