Research map / Bandits and online learning / RL theory and MDPs
Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty Equivalents
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 OCE-VI for learning recursive OCE MDPs | Tabular episodic MDPs with recursive OCEs · Recursive OCE MDPs | regret dependence on episodes and actions: optimal dependence on the number of episodes K and the number of actions A, up to logarithmic factors | Helped |
| Use the OCE-VI exploration bonus instead of the ICVaR exploration bonus | Iterated CVaR MDPs · Iterated CVaR MDPs, 0 < α ≤ (3 − √5)/2 | regret upper bound: improves the result of [cite] by a factor of H^2 | Helped |
| Use OCE-VI rather than RSVI2 or RSQ2 | Entropic-risk MDPs · Randomly generated MDP instances | performance | Mixed |
| Use a Bernstein-style exploration bonus instead of the current bonus (ablation) | OCE-VI · Recursive OCE MDPs | regret upper bound | No clear effect |
Closest papers by meaning
- A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents (ICML 2025 · similarity 0.91)
- Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning (ICML 2024 · similarity 0.89)
- Achieving Constant Regret in Linear Markov Decision Processes (NeurIPS 2024 · similarity 0.88)
- Provably Efficient Partially Observable Risk-sensitive Reinforcement Learning with Hindsight Observation (ICML 2024 · similarity 0.88)
- Online Learning in Risk Sensitive constrained MDP (ICML 2025 · similarity 0.88)
- Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents (NeurIPS 2025 · 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.