Research map / Bandits and online learning / RL theory and MDPs
Model-free Reinforcement Learning in Infinite-horizon Average-reward 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 discounted optimistic Q-learning for the undiscounted problem | Optimistic Q-learning · Weakly communicating infinite-horizon average-reward MDPs | regret: \otil(T^{2/3}) | Helped |
| Use per-state optimistic online mirror descent to optimize the policy directly | MDP-OOMD · Ergodic infinite-horizon average-reward MDPs | expected regret: \otil(\sqrt{T}) versus \otil(T^{3/4}) | Helped |
| Use MDP-OOMD instead of Politex | Model-free learning in ergodic MDPs · Ergodic infinite-horizon average-reward MDPs | regret: \mix^3\hit\sqrt{SA}T^\frac{3}{4} -> \otil(\sqrt{\mix^3 \rho AT}) | Helped |
Closest papers by meaning
- Horizon-Free Regret for Linear Markov Decision Processes (ICLR 2024 · similarity 0.90)
- A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs (ICML 2025 · similarity 0.90)
- Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes (AAAI 2024 · similarity 0.90)
- Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs (ICLR 2024 · similarity 0.90)
- Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback (ICML 2025 · similarity 0.89)
- Dynamic Regret of Adversarial MDPs with Unknown Transition and Linear Function Approximation (AAAI 2024 · similarity 0.89)
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.