Research map / Bandits and online learning / RL theory and MDPs
Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning
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 staged exploration and policy elimination with a pre-specified batch schedule | Tabular episodic multi-batch RL · Tabular episodic MDP, K episodes | regret upper bound: \tilde{O}\left( \sqrt{SAH^3K\iota^2} + S^{\frac{15}{4}}A^{\frac{9}{8}}H^{\frac{17}{8}}\iota^{\frac{5}{8}}K^{\frac{3}{8}} | Helped |
| Use staged exploration and policy elimination with a pre-specified batch schedule | Tabular episodic multi-batch RL · Tabular episodic MDP, K episodes | batch complexity: O(H +\log_2\log_2(K)) | Helped |
| Require regret O(poly(S,A,H)\sqrt{K}) | Any multi-batch RL algorithm · Tabular episodic MDP, K episodes | batch complexity lower bound: \Omega(H/\log_A(K)+\log_2\log_2(K)) | Hurt |
Closest papers by meaning
- Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints (ICML 2024 · similarity 0.90)
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 2024 · similarity 0.90)
- Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching (NeurIPS 2026 · similarity 0.89)
- Achieving Constant Regret in Linear Markov Decision Processes (NeurIPS 2024 · similarity 0.89)
- Switching the Loss Reduces the Cost in Batch Reinforcement Learning (ICML 2024 · similarity 0.89)
- Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach (NeurIPS 2025 · similarity 0.88)
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.