Research map / Bandits and online learning / RL theory and MDPs
Near Optimal Exploration-Exploitation in Non-Communicating 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 TUCRL's truncation of low-confidence transitions to unvisited states | TUCRL versus UCRL · Taxi with misspecified states | cumulative regret | Helped |
| Use TUCRL instead of UCRL | Taxi with communicating state space · Communicating taxi | cumulative regret | No clear effect |
| Use TUCRL instead of SCAL with prior knowledge of the bias-span bound | Three-state weakly-communicating domain · Three-state domain with infinite diameter | cumulative regret | Mixed |
| Enable transitions to unvisited states periodically during exploratory episodes | TUCRL · Three-state domain with infinite diameter | cumulative regret | Hurt |
| Use a looser relaxed transition-confidence bound during initial exploration | TUCRL versus UCRL · Communicating taxi | cumulative regret | Hurt |
| Require efficient learning with polynomial-time sublinear regret without prior knowledge | Any learning algorithm · Weakly-communicating MDPs | regret growth | Hurt |
Closest papers by meaning
- Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning (ICML 2018 · similarity 0.92)
- Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs (NeurIPS 2019 · similarity 0.91)
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 2024 · similarity 0.90)
- Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret (NeurIPS 2026 · similarity 0.89)
- Achieving Tractable Minimax Optimal Regret in Average Reward MDPs (NeurIPS 2024 · similarity 0.88)
- Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback (ICML 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.