AI Paper Atlas

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

ICLR 2026 · Reinforcement learning › MDPs and planning · approach: Average-reward and regularized MDPs · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
plan with MCTS on the occupancy MDP instead of using the infinite-trials optimal policypi_Solver · Entropy max. FrozenLakeF_{1,H} (lower better): 0.48 -> 0.40Improved
plan with MCTS on the occupancy MDP instead of the infinite-trials optimal policypi_Solver · Entropy max. illustrative GUMDPF_{1,H} (lower better): 0.05 -> 0.01Improved
plan with MCTS instead of infinite-trials policypi_Solver · Imitation learning TaxiF_{1,H} (lower better): 0.05 -> 0.05No clear effect
plan with MCTS instead of infinite-trials policypi_Solver · Imitation learning MountainCarF_{1,H} (lower better): 0.07 -> 0.04Improved
plan with MCTS instead of infinite-trials policypi_Solver · Adversarial MDPF_{1,H} (lower better): 1.17 -> 1.07Improved
use history-dependent (non-Markovian) policies instead of stationary or Markovian onesGUMDP single-trial policies · constructed GUMDPF_1Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy