Research map / Bandits and online learning / RL theory and MDPs
Online Convex Optimization in Adversarial 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 UC-O-REPS with entropic online mirror descent and confidence sets for unknown transitions | episodic loop-free adversarial MDPs · Convexly-measurable performance criteria | regret upper bound: 15 F L|X| \sqrt{T |A|\ln{\frac{T|X||A|}{\delta}}} | Helped |
| Use UC-O-REPS instead of the prior adversarial-MDP bound | adversarial MDPs with unknown transitions · Expected average loss | regret upper bound: \tilde{O}(L|X||A|\sqrt{T}) to achieve \tilde{O}(L|X|\sqrt{|A|T}) | Helped |
| Extend the criterion beyond total expected loss to convex performance criteria | UC-O-REPS · Convex performance criteria, including risk-sensitive and robust objectives | regret guarantee | Helped |
| Combine online mirror descent with UCRL-2-style confidence sets | UC-O-REPS · Unknown-transition adversarial MDPs | regret upper bound: \tilde{O}(L|X|\sqrt{|A|T}) | Helped |
Closest papers by meaning
- Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback (NeurIPS 2025 · similarity 0.92)
- Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback (ICML 2025 · similarity 0.91)
- Online Episodic Convex Reinforcement Learning (ICML 2025 · similarity 0.91)
- Online Learning in CMDPs: Handling Stochastic and Adversarial Constraints (ICML 2024 · similarity 0.90)
- Learning Adversarial MDPs with Stochastic Hard Constraints (ICML 2025 · similarity 0.90)
- Rate-Optimal Policy Optimization for Linear Markov Decision Processes (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.