Research map / Bandits and online learning / RL theory and MDPs
Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition
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 |
|---|---|---|---|
| Replace total-variation confidence set per state-action pair with a tighter independent per-(x,a,x') confidence set (ablation) | UOB-REPS · adversarial episodic MDP, unknown transition, bandit feedback | regret bound: removes an extra |X| factor | Helped |
| Use upper occupancy bound (optimistic, inversely weighted loss estimator) instead of plug-in occupancy estimate bqt | UOB-REPS · adversarial episodic MDP, unknown transition, bandit feedback | regret bound: from O~(T^{3/4}) to O~(sqrt(T)) | Helped |
Closest papers by meaning
- Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback (NeurIPS 2025 · similarity 0.94)
- Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback (NeurIPS 2024 · similarity 0.93)
- Dynamic Regret of Adversarial MDPs with Unknown Transition and Linear Function Approximation (AAAI 2024 · similarity 0.91)
- Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback (ICML 2025 · similarity 0.91)
- Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback (ICLR 2024 · similarity 0.91)
- Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback (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.