AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics

Zhiao Huang, Yuanming Hu, Tao Du, Siyuan Zhou, Hao Su, Joshua B. Tenenbaum, Chuang Gan

ICLR 2021 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 15 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
optimize open-loop action sequences with differentiable physics and AdamPlasticineLab gradient-based planning · Move, Tri. Move, Rope, RollingPin, Chopsticks, Assemblynormalized incremental IoUImproved
use Adam instead of gradient descent with momentum (ablation)PlasticineLab gradient-based planning · Move, Tri. Move, Rope, Pinch, RollingPin, Chopsticks, Assemblynormalized incremental IoU: Move: 0.51\pm 0.39 -> 0.90\pm 0.12; Tri. Move: 0.24\pm 0.17 -> 0.35\pm 0.20; Rope: 0.41\pm 0.17 -> 0.59\pm 0.13; Pinch: Mixed
use softened contact rather than hard contact to compute gradients (ablation)Adam trajectory optimization · most PlasticineLab tasksnormalized incremental IoUImproved
increase yield stress (ablation)SAC on Move · MoverewardImproved
increase yield stress above 100 (ablation)SAC on Move · MoverewardNo clear effect
increase manipulators and plasticine boxes in the taskRL algorithms · Tri. Movenormalized incremental IoUHurt
use gradient-based trajectory optimization instead of RLPlasticineLab planning · Rope, Chopsticks, Assemblynormalized incremental IoUImproved
apply local gradient-based optimization to tasks requiring detachment and reattachment or multiple stagesgradient-based planning · Pinch and Writernormalized incremental IoUHurt

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