Research map / Bandits and online learning / RL theory and MDPs
Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function
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 |
|---|---|---|---|
| Use state-pair differences of the optimal bias function to build a confidence set for OFU exploration | EBF · Weak-communicating MDPs, H known | regret upper bound: \tilde{O}(H\sqrt{SAT}) -> \tilde{O}(\sqrt{SAHT}) | Helped |
| Use EBF without prior knowledge of the bias span, relying on finite diameter D | EBF · Weak-communicating MDPs with finite unknown diameter D | regret upper bound: \tilde{O}(\sqrt{SADT}) | Helped |
| Use the state-pair bias-difference regret bound for finite-diameter MDPs | EBF · MDPs with finite diameter D | regret upper bound: \tilde{O}(\sqrt{SADT}) versus \Omega(\sqrt{SADT}) | No clear effect |
Closest papers by meaning
- Achieving Tractable Minimax Optimal Regret in Average Reward MDPs (NeurIPS 2024 · similarity 0.92)
- Achieving Constant Regret in Linear Markov Decision Processes (NeurIPS 2024 · similarity 0.91)
- Horizon-Free Regret for Linear Markov Decision Processes (ICLR 2024 · similarity 0.90)
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 2024 · similarity 0.90)
- No-Regret Reinforcement Learning in Smooth MDPs (ICML 2024 · similarity 0.90)
- Minimax Optimal Reinforcement Learning with Quasi-Optimism (ICLR 2025 · 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.