Research map / Bandits and online learning / RL theory and MDPs
Optimistic posterior sampling for reinforcement learning: worst-case regret bounds
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace optimistic deterministic bias with multi-sample posterior sampling (boosted Dirichlet, ~O(S) samples per state-action) in an extended MDP | UCRL2-style epoch-based RL · communicating MDPs, worst-case regret | regret bound dependence on S: sqrt(S) factor improvement (O(D sqrt(SAT)) vs O(DS sqrt(AT))) | Helped |
Closest papers by meaning
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 2024 · similarity 0.95)
- Why is Posterior Sampling Better than Optimism for Reinforcement Learning? (ICML 2017 · similarity 0.94)
- Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees (NeurIPS 2022 · similarity 0.93)
- Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces (ICML 2026 · similarity 0.93)
- No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes (NeurIPS 2025 · similarity 0.91)
- Achieving Constant Regret in Linear Markov Decision Processes (NeurIPS 2024 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.