AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control

Nolan Wagener, Andrey Kolobov, Felipe Vieira Frujeri, Ricky Loynd, Ching-An Cheng, Matthew Hausknecht

NeurIPS 2022 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Imitation and skill learning · 4 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 reward-weighted regression instead of unweighted behavioral cloning (ablation)Multi-clip tracking policy · CMU MoCap snippetsaverage normalized episode reward: 0.654 ± 0.005 -> 0.688 ± 0.002; 5% improvement over BCImproved
Add clip-weighted regression instead of unweighted behavioral cloning (ablation)Multi-clip tracking policy · CMU MoCap snippetsaverage normalized episode reward: 0.654 ± 0.005 -> 0.671 ± 0.003; 3% improvement over BCImproved
Add advantage-weighted regression instead of unweighted behavioral cloning (ablation)Multi-clip tracking policy · CMU MoCap snippetsaverage normalized episode reward: 0.654 ± 0.005 -> 0.661 ± 0.003; 1% improvement over BCImproved
Reuse a pretrained general low-level policy rather than train with no low-level policy (ablation)Humanoid reinforcement-learning transfer · Go-to-targetreturn: 7.5 ± 1.1 -> 96.3 ± 2.8Improved
Restrict the pretrained low-level policy to locomotion clips rather than use the general policy (ablation)Humanoid reinforcement-learning transfer · Go-to-targetreturn: 96.3 ± 2.8 -> 66.1 ± 32.8Hurt
Reuse a pretrained general low-level policy rather than train with no low-level policy (ablation)Humanoid reinforcement-learning transfer · Velocity controlreturn: 1157 ± 89 vs. 1074 ± 55Mixed
Restrict the pretrained low-level policy to locomotion clips rather than use the general policy (ablation)Humanoid reinforcement-learning transfer · Velocity controlreturn: 1074 ± 55 -> 884 ± 81Hurt
Use stochastic expert rollouts with action noise rather than deterministic expert behavior (ablation)Clip snippet experts · CMU MoCap snippetsaverage normalized episode reward: deterministic mean 0.816; noisy mean 0.689Hurt
Increase the intention prior autoregressive parameter from α = 0 to α = 0.95 (ablation)RWR multi-clip policy · CMU MoCap snippetspolicy performance: 3% improvementImproved

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