Research map / Bandits and online learning / RL theory and MDPs
Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space
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 |
|---|---|---|---|
| increase arrival rate lambda (0.3, 0.5, 0.7) | Thompson-sampling-based algorithm (TSDE) for countable-state MDPs · Two-server queueing system with common buffer | Bayesian regret | Hurt |
| increase arrival rate lambda (0.3, 0.5, 0.7) with PPO-learned policy within weighted-routing class | TSDE with PPO policy oracle · Two heterogeneous parallel queues | Bayesian regret | Hurt |
| run algorithm over longer horizon (more transitions) | TSDE · Both queueing models | regret growth | Helped |
Closest papers by meaning
- Learning Unknown Markov Decision Processes: A Thompson Sampling Approach (NeurIPS 2017 · similarity 0.90)
- Finding good policies in average-reward Markov Decision Processes without prior knowledge (NeurIPS 2024 · similarity 0.89)
- Achieving Tractable Minimax Optimal Regret in Average Reward MDPs (NeurIPS 2024 · similarity 0.88)
- Near-Optimal Sample Complexity for MDPs via Anchoring (ICML 2025 · similarity 0.88)
- Optimal Sample Complexity for Average Reward Markov Decision Processes (ICLR 2024 · similarity 0.87)
- Online Markov Decision Processes Configuration with Continuous Decision Space (AAAI 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.