AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning

Fuyuan Qian, Menglong Zhang, Song Wang, Quanying Liu

ICML 2026 · Reinforcement learning › Offline RL · approach: Diffusion models for offline decision making · 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
add world-model objective L_WM for task representation (ablation)MetaSTAR · 8 offline meta-RL environmentsreturnImproved
add conservative policy optimization (ablation)MetaSTAR · 8 offline meta-RL environmentsreturnImproved
combine L_WM and conservative policy optimization (ablation)MetaSTAR · sparse-reward environmentsreturnImproved
add conservative policy optimization (ablation)MetaSTAR · Hopper-ParamreturnHurt
use MetaSTAR instead of CORROMetaSTAR · Cheetah-Vel-Sparse (online)average return: 216 -> 260Improved
use MetaSTAR instead of UNICORNMetaSTAR · Ant-Dir online testaverage return: 149 -> 230Improved
use MetaSTAR instead of CORROMetaSTAR · Hopper-Param (online)average return: 294 -> 279Hurt
use MetaSTAR instead of UNICORNMetaSTAR · Ant-Dir OOD tasksaverage return: 1 -> 59Improved

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