Research map / Bandits and online learning / RL theory and MDPs
Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function 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 |
|---|---|---|---|
| Use an empirical Bernstein transition bonus based on next-state value variance, with a value-function uncertainty correction | EULER · Episodic tabular MDPs | leading-term regret upper bound: \tilde O(\sqrt{HSAT}) -> \tilde O(\sqrt{\ComplexityQ{} SAT}) | Helped |
| Use EULER when total episode reward is bounded by 1 | EULER · Episodic MDPs with total reward bounded by 1 | leading-term regret upper bound: \tilde O \left( \sqrt{SAK} + \LowerOrderTerm \right) . | Helped |
| Use EULER in deterministic-reward, deterministic-transition MDPs | EULER · Deterministic MDPs | regret dependence on T: log(T) -> \sqrt{T} | Helped |
| Use EULER in a chain MDP with low next-state value variance | EULER · Chain MDP (N = H = S) | regret upper bound: \tilde O (\sqrt{N^3AK} + \dots) -> \tilde O (\sqrt{NAK} + \dots) | Helped |
| Use EULER when transitions are sampled from a fixed distribution independent of state and action | EULER · Tabular contextual bandits | leading-term regret upper bound: \tilde O \( \sqrt{SAT} + \LowerOrderTerm{} \) | Helped |
Closest papers by meaning
- Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning (NeurIPS 2021 · similarity 0.94)
- Minimax Regret Bounds for Reinforcement Learning (ICML 2017 · similarity 0.92)
- Horizon-Free Regret for Linear Markov Decision Processes (ICLR 2024 · similarity 0.91)
- Position: Constants are Critical in Regret Bounds for Reinforcement Learning (ICML 2025 · similarity 0.91)
- Achieving Constant Regret in Linear Markov Decision Processes (NeurIPS 2024 · similarity 0.90)
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 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.