AI Paper Atlas

Research map / Reinforcement learning / Offline RL

SOLAR for Offline MARL: Plateau-Triggered Potential Shaping under World-Model Uncertainty

Jusheng Zhang, Yijia Fan, Ruiqi Chen, Jing Yang, Ziliang Chen, Yongsen Zheng, Yanxi Chen, Jian Wang, Kwok-Yan Lam, Liang Lin, Keze Wang

ICML 2026 · Reinforcement learning › Offline RL · approach: Offline RL sample complexity theory

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 adaptive reward shaping (ARS) module (ablation)SOLAR · SMAC 5m vs 6m (Medium data)win rate (%): 72.3 -> 83.45Improved
use stagnation-triggered shaping instead of static shaping (ablation)SOLAR · SMAC 5m vs 6m (Medium data)win rate (%): 78.1 -> 83.45Improved
combine all three reward components (ct, dt, et) rather than any single one (ablation)SOLAR · SMAC 5m vs 6m (Medium data)win rate (%): 75.4 -> 83.45 (best single ct)Improved
add the world model (WM) as training substrate (ablation)SOLAR · SMAC 5m vs 6m (Medium data)win rate (%): 64.5 -> 72.3Improved
use SOLAR instead of offline baselines on low-quality dataSOLAR · SMAC 5m vs 6m (Poor data)win rate (%): 44.2 -> 58.17Improved
conservative CQL-style objective with SOLAR training versus offline IQLSOLAR · SMAC 5m vs 6m (Medium data) OOD Q-valuesOOD Q-value overestimationImproved

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