AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Demystifying Action Space Design for Robotic Manipulation Policies

Yuchun Feng, Jinliang Zheng, Zhihao Wang, Dongxiu Liu, Jianxiong Li, Jiangmiao Pang, Tai Wang, Xianyuan Zhan

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 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
predict delta actions instead of absolute actions (ablation)EE-space ACT policy · Single Arm AgileX, averageprogress score: 69.0 -> 89.6Improved
predict delta actions instead of absolute actions (ablation)Joint-space DP policy · Single Arm AgileX, averageprogress score: 85.0 -> 95.9Improved
predict delta actions instead of absolute actions (ablation)Joint-space ACT policy · RoboTwin 2.0success rate: 40.0 -> 46.3Improved
predict delta actions instead of absolute actions (ablation)Joint-space DP policy · Bimanual AgileX Bowlprogress score: 74.7 -> 74.6No clear effect
use chunk-wise delta instead of step-wise delta (ablation)regression policy on single-arm AgileX · Touch Cube, Pick Up Cup, Pick and Place Cupprogress score: gap upwards of 10% on averageImproved
use shorter execution horizon for delta and longer for absolute actions (ablation)action chunking · Single Arm AgileX, execution horizon 15 to 60progress scoreImproved
use joint space instead of task (EE) space with flow-matching policy (ablation)DP policy · Single Arm AgileX, averageprogress score: 91.4 -> 95.9 (delta)Improved
use joint space instead of task (EE) space with regression policy (ablation)ACT policy, delta actions · Single Arm AgileX, averageprogress score: 89.6 -> 88.0No clear effect
increase training epochs and demonstrations (ablation)joint-space policies · Single Arm AgileX scalingprogress scoreImproved
use task-space instead of joint-space actions (ablation)cross-embodiment and pi0 transfer learning · AgileX and AIRBOTprogress scoreMixed

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