Research map / Learning theory and algorithms / Sample complexity
Planning in Markov Decision Processes with Gap-Dependent Sample Complexity
Anders Jonsson, Emilie Kaufmann, Pierre Menard, Omar Darwiche Domingues, Edouard Leurent, Michal Valko
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 MDP-GapE (UGapE at root plus optimistic planning) instead of Sparse Sampling | fixed-confidence planning · Random MDPs, epsilon=1 | oracle calls: 8e9 -> 1.9e4 (max n) | Improved |
| use MDP-GapE instead of Sparse Sampling | fixed-confidence planning · Random MDPs, epsilon=0.2 | oracle calls: 3e16 -> 2.3e6 (max n) | Improved |
| compare empirical to theoretical epsilon scaling | MDP-GapE · Random MDPs | exponent of 1/epsilon: 8.4 -> 3.9 | Improved |
| use MDP-GapE instead of KL-OLOP, BRUE, UCT in fixed-budget setting | planning · Random MDPs fixed budget | simple regret | Mixed |
Closest papers by meaning
- Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process (NeurIPS 2024 · similarity 0.88)
- Threshold UCT: Cost-Constrained Monte Carlo Tree Search with Pareto Curves (AAAI 2025 · similarity 0.88)
- Power Mean Estimation in Stochastic Continuous Monte-Carlo Tree Search (ICML 2025 · similarity 0.87)
- Tree Search-Based Policy Optimization under Stochastic Execution Delay (ICLR 2024 · similarity 0.87)
- Graph Sparse Sampling: Breaking the Curse of the Horizon in Continuous MDP Planning (NeurIPS 2026 · similarity 0.87)
- A Surprisingly Simple Continuous-Action POMDP Solver: Lazy Cross-Entropy Search Over Policy Trees (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.
