Why Is Posterior Sampling Better Than Optimism For Reinforcement Learning?

Abstract

Computational results demonstrate that posterior sampling for reinforcement learning (PSRL) dramatically outperforms algorithms driven by optimism, such as UCRL2. We provide insight into the extent of this performance boost and the phenomenon that drives it. We leverage this insight to establish an \(\tilde\{O\}(H\sqrt\{SAT\})\) Bayesian expected regret bound for PSRL in finite-horizon episodic Markov decision processes, where \(H\) is the horizon, \(S\) is the number of states, \(A\) is the number of actions and \(T\) is the time elapsed. This improves upon the best previous bound of \(\tilde\{O\}(H S \sqrt\{AT\})\) for any reinforcement learning algorithm.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyosband2016why

Related papers

• Optimistic Posterior Sampling For Reinforcement Learning With Few Samples And Tight Guarantees (2022)0.00
• Model-based Reinforcement Learning For Continuous Control With Posterior Sampling (2020)0.00
• Posterior Sampling For Large Scale Reinforcement Learning (2017)0.00
• Posterior Sampling For Continuing Environments (2022)0.00
• Q-learning With Posterior Sampling (2025)0.00
• Breaking The Sample Complexity Barrier To Regret-optimal Model-free Reinforcement Learning (2021)0.00
• Provably Efficient Exploration In Constrained Reinforcement Learning:posterior Sampling Is All You Need (2023)0.00
• Successor Uncertainties: Exploration And Uncertainty In Temporal Difference Learning (2018)0.00