Research map / Bandits and online learning / RL theory and MDPs
Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes
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 Bernstein-type confidence set (model-optimistic) or variance-dependent MVP bonus (value-optimistic) in LMDP planning | LMDP with context in hindsight · theoretical regret analysis | regret dependence on horizon H | Helped |
| Replace Azuma-type dependence with variance-dependent bound (sqrt(Var* M Γ S A K)) instead of sqrt(H)-scaling bound | LMDP regret · theoretical regret analysis | regret order in Var* | Helped |
| Scale the number of states dependence from S (prior) to sqrt(S Γ) | LMDP regret · theoretical comparison | regret dependence on S | Helped |
| Upper bound matched by lower bound with Γ=2 (minimax optimal for constant Γ) | variance-bounded LMDPs · theoretical lower bound comparison | optimality gap | No clear effect |
Closest papers by meaning
- Horizon-Free Regret for Linear Markov Decision Processes (ICLR 2024 · similarity 0.93)
- Achieving Constant Regret in Linear Markov Decision Processes (NeurIPS 2024 · similarity 0.93)
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 2024 · similarity 0.91)
- Achieving Tractable Minimax Optimal Regret in Average Reward MDPs (NeurIPS 2024 · similarity 0.91)
- No-Regret Reinforcement Learning in Smooth MDPs (ICML 2024 · similarity 0.90)
- Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback (ICML 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.