AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning

Jiayu Chen, Le Xu, Wentse Chen, Jeff Schneider

ICLR 2026 · Reinforcement learning › Offline RL · approach: Simple practical offline RL · 6 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
add Bayesian belief adaptation over ensemble members (ablation)offline MBRL world model · D4RL imagined rolloutsprediction error: 10 of 12 tasks lower errorImproved
add belief adaptation (ablation)world model · D4RL Hopper randomoverall prediction error: 0.106 -> 0.122Hurt
add belief adaptation (ablation)world model · D4RL medium Hopperoverall prediction error: 34.40 -> 9.727Improved
add belief adaptation to Optimized (BA-MBRL) (ablation)Optimized · Tokamak tracking (average)average return: -70.98 -> -28.03Improved
add continuous BAMCP planner on top of BA-MBRL (ablation)BA-MBRL · Tokamak tracking (average)average return: -28.03 -> -20.61Improved
replace SAC distillation with supervised learning (ablation)BA-MCTS · Tokamak tracking (average)average return: -20.61 -> -24.11Mixed
replace SAC distillation with supervised learning (ablation)BA-MCTS · D4RL Walker2dstabilityHurt
remove pessimistic reward penalty (lambda=0) (ablation)BA-MCTS · D4RL MuJoCo (average)normalized scoreHurt
use BA-MCTS instead of MOBILEoffline MBRL · D4RL MuJoCo (average)normalized score: 76.50 -> 80.25Improved
use BA-MCTS instead of APE-V (model-free BAMDP)offline RL · D4RL MuJoConormalized score: 72.65 -> 80.25Improved
use BA-MCTS instead of Sampled EfficientZero searchoffline RL · D4RL MuJoConormalized scoreImproved

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