Research map / Bandits and online learning / RL theory and MDPs
Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time
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 the proposed model-free algorithm instead of UCBVI-$\gamma$ | Online discounted tabular MDP learning · Tabular infinite-horizon discounted MDPs | range of T with optimality: $\Big[\frac{S^3A^2}{(1-\gamma)^4}, \infty\Big)$ -> $\Big[\frac{SA}{(1-\gamma)^{13}}, \infty\Big)$ | Helped |
| Use the proposed model-free algorithm instead of UCBVI-$\gamma$ | Online discounted tabular MDP learning · Tabular infinite-horizon discounted MDPs | space complexity: $S^2A$ -> $SA$ | Helped |
| Apply reference-advantage variance reduction | Proposed algorithm · Tabular infinite-horizon discounted MDPs | cumulative regret | Helped |
| Switch the execution policy adaptively when Q-estimate staleness exceeds a threshold | Proposed algorithm · Tabular infinite-horizon discounted MDPs | cumulative regret | Helped |
| Use a predetermined, exponentially phased policy-switching schedule instead of adaptive switching | Execution policy switching · Tabular infinite-horizon discounted MDPs | cumulative regret | Hurt |
Closest papers by meaning
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 2024 · similarity 0.90)
- Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
- Achieving Tractable Minimax Optimal Regret in Average Reward MDPs (NeurIPS 2024 · similarity 0.89)
- Horizon-Free Regret for Linear Markov Decision Processes (ICLR 2024 · similarity 0.89)
- Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback (ICML 2025 · similarity 0.89)
- A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs (ICML 2024 · similarity 0.89)
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.