AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Efficient Offline Policy Optimization with a Learned Model

Zichen Liu, Siyi Li, Wee Sun Lee, Shuicheng YAN, Zhongwen Xu

ICLR 2023 · Reinforcement learning › Offline RL · approach: Offline RL sample complexity theory · 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
replace MCTS policy improvement with regularized one-step look-aheadMuZero Unplugged · RL Unplugged Atari (12 games)IQM normalized score: 151% -> 194%Improved
replace MCTS with one-step look-aheadMuZero Unplugged · RL Unplugged Atari (12 games), reaching 150% IQM normalized scorewall-clock time: 5.6%Improved
use ROSMO instead of MZUoffline RL agents · Catch, MountainCar, and Cartpoleepisode returnMixed
use one-step look-ahead rather than multi-step MCTS planningMZU · BSuite with stochastic transitionsepisode return: 0.980 ± 0.060 -> 1.0 ± 0.0; 0.984 ± 0.054 -> 1.0 ± 0.0; 0.772 ± 0.253 -> 0.900 ± 0.237; 0.404 ± 0.422 -> 0.916 ± 0.139Improved
use ROSMO instead of MZU in the low-data regimeoffline RL agents · BSuite, sub-sampled datasetsIQM normalized scoreImproved
use ROSMO instead of MZU across dynamics model capacitiesoffline RL agents · BSuite, 10% dataIQM normalized scoreImproved
limit MZU search depthMZU · BSuiteIQM normalized scoreImproved
reduce MZU simulation budgetMZU · BSuiteIQM normalized scoreHurt
use deep MZU search with high simulation budgetMZU · BSuiteIQM normalized scoreHurt
replace standard MZU policy targets with MPO-style Q-based policy updates (ablation)MZU · MsPacman with 4 simulationsIQM normalized scoreImproved
sample actions for policy improvement under a limited sampling budget (ablation)ROSMO · MsPacman with 4 samplesIQM normalized scoreImproved
reduce model unroll length from 5 to 1 (ablation)ROSMO · MsPacmanIQM normalized scoreNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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