Research map / Bandits and online learning / RL theory and MDPs
Regret Minimization in MDPs with Options without Prior Knowledge
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 |
|---|---|---|---|
| parameter-free option model (irreducible MC + nested EVI, FSUCRLv2) instead of SUCRL with known option parameters | learning in MDPs with options · 14x14 four-rooms maze | cumulative regret: roughly half the regret of UCRL | Helped |
| explicit confidence intervals on stationary distribution (FSUCRLv1) instead of nested EVI (FSUCRLv2) (ablation) | FSUCRL · 14x14 four-rooms maze | cumulative regret | Hurt |
| parameter-free FSUCRL vs SUCRL with prior knowledge on option parameters | learning with options · grid-world | regret | Helped |
| use of options (temporal abstraction) in FSUCRL vs learning without options (UCRL) | learning with options · 20x20 grid-world | regret | Helped |
Closest papers by meaning
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 2024 · similarity 0.89)
- No-Regret Reinforcement Learning in Smooth MDPs (ICML 2024 · similarity 0.88)
- Achieving Constant Regret in Linear Markov Decision Processes (NeurIPS 2024 · similarity 0.87)
- Achieving Tractable Minimax Optimal Regret in Average Reward MDPs (NeurIPS 2024 · similarity 0.87)
- Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes (AAAI 2024 · similarity 0.87)
- Horizon-Free Regret for Linear Markov Decision Processes (ICLR 2024 · similarity 0.87)
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.