AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Hierarchical Value-Decomposed Offline Reinforcement Learning for Whole-Body Control

Zhilong Zhang, Yunpeng Mei, Xinghao Du, Hongjie Cao, Haonan Wang, Pengyuan Min, Chenyu Wang, Pengfei Chen, Chenbo Xin, Yijie Wang, Wenyu Luo, Yihao Sun and 4 more

ICLR 2026 · Reinforcement learning › Imitation learning · approach: Imitation combined with RL

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 hierarchical Q-value decomposition (vs shared Q-value) (ablation)HVD with DP · WB-50, average over 5 taskssuccess rate: -0.03Improved
add hierarchical Q-value decomposition (vs shared Q-value) (ablation)HVD with WB-VIMA · WB-50, average over 5 taskssuccess rate: -0.07Improved
add hierarchical Q-value decomposition (vs shared Q-value) (ablation)HVD with π0 · WB-50, average over 5 taskssuccess rate: -0.05Improved
add hierarchical Q-value decomposition (vs shared Q-value) (ablation)HVD with π0 · WB-50 Pen Insertsuccess rate: +0.04Hurt
add hierarchical Q-value decomposition (vs shared Q-value) (ablation)HVD with π0 · WB-50 Wipe Boardsuccess rate: -0.14Improved
add hierarchical Q-value decomposition (vs shared Q-value) (ablation)HVD with WB-VIMA · WB-50 Wipe Boardsuccess rate: -0.12Improved
train HVD on mixed-quality data instead of IL on expert-only dataπ0 · WB-50, average over 5 taskssuccess rate: 0.44 -> 0.58Improved
train HVD on mixed-quality data instead of IL on expert-only dataWB-VIMA · WB-50, average over 5 taskssuccess rate: 0.30 -> 0.46Improved
train HVD on mixed-quality data instead of IL on expert-only dataDiffusion Policy · WB-50, average over 5 taskssuccess rate: 0.26 -> 0.32Improved
train HVD on mixed-quality data instead of IL on expert-only dataWB-VIMA · WB-50 Basket Carrysuccess rate: 0.10 -> 0.10No clear effect
train HVD on mixed-quality data instead of IL on expert-only dataDiffusion Policy · WB-50 Wipe Boardsuccess rate: 0.00 -> 0.00No clear effect
train one multi-task policy instead of per-task specialistsπ0 IL · WB-50, average over 5 taskssuccess rate: 0.44 -> 0.36Hurt

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