Research map / Bandits and online learning / RL theory and MDPs
Oracle-Efficient Regret Minimization in Factored MDPs with Unknown Structure
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 |
|---|---|---|---|
| Learn unknown scopes using consistent-scope elimination with optimistic regret minimization | SLF-UCRL · SysAdmin, circular topology with 4 state factors | regret | Helped |
| Ignore the factored structure | UCRL versus SLF-UCRL · SysAdmin, circular topology with 4 state factors | regret | Hurt |
| Learn all factor scopes instead of using structure knowledge | SLF-UCRL4 versus Factored-UCRL · SysAdmin, circular topology with 4 state factors | regret | No clear effect |
Closest papers by meaning
- Achieving Tractable Minimax Optimal Regret in Average Reward MDPs (NeurIPS 2024 · similarity 0.90)
- Eluder-based Regret for Stochastic Contextual MDPs (ICML 2024 · similarity 0.89)
- Achieving Constant Regret in Linear Markov Decision Processes (NeurIPS 2024 · similarity 0.88)
- No-Regret Reinforcement Learning in Smooth MDPs (ICML 2024 · similarity 0.88)
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 2024 · similarity 0.88)
- Truly No-Regret Learning in Constrained MDPs (ICML 2024 · 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.