Research map / Reinforcement learning / MDPs and planning
Solving General-Utility Markov Decision Processes in the Single-Trial Regime with Online Planning
Pedro Pinto Santos, Alberto Sardinha, Francisco S. Melo
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 |
|---|---|---|---|
| plan with MCTS on the occupancy MDP instead of using the infinite-trials optimal policy | pi_Solver · Entropy max. FrozenLake | F_{1,H} (lower better): 0.48 -> 0.40 | Improved |
| plan with MCTS on the occupancy MDP instead of the infinite-trials optimal policy | pi_Solver · Entropy max. illustrative GUMDP | F_{1,H} (lower better): 0.05 -> 0.01 | Improved |
| plan with MCTS instead of infinite-trials policy | pi_Solver · Imitation learning Taxi | F_{1,H} (lower better): 0.05 -> 0.05 | No clear effect |
| plan with MCTS instead of infinite-trials policy | pi_Solver · Imitation learning MountainCar | F_{1,H} (lower better): 0.07 -> 0.04 | Improved |
| plan with MCTS instead of infinite-trials policy | pi_Solver · Adversarial MDP | F_{1,H} (lower better): 1.17 -> 1.07 | Improved |
| use history-dependent (non-Markovian) policies instead of stationary or Markovian ones | GUMDP single-trial policies · constructed GUMDP | F_1 | Improved |
Closest papers by meaning
- The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes (ICML 2025 · similarity 0.93)
- Online Markov Decision Processes Configuration with Continuous Decision Space (AAAI 2024 · similarity 0.89)
- Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes (AAAI 2024 · similarity 0.89)
- Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm (NeurIPS 2024 · similarity 0.88)
- On the Convergence of Success Conditioning for Policy Optimization (NeurIPS 2026 · similarity 0.88)
- Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs (NeurIPS 2026 · 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.
