AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

CoMic: Complementary Task Learning & Mimicry for Reusable Skills

Leonard Hasenclever, Fabio Pardo, Raia Hadsell, Nicolas Heess, Josh Merel

ICML 2020 · 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
Use MLP low-level policy instead of LSTM, mixture, or product architectureslow-level policy architecture · Go To Target, Gaps, Walls transfer across data regimesmean return on transfer tasksImproved
Joint training with complementary get-up task (10% of episodes) (ablation)MLP low-level policy on largest mocap set · Get-up and stand tasktask performanceImproved
Joint training with ball catching task (20% of episodes) (ablation)MLP low-level policy on largest mocap set · Ball catching tasktask performanceImproved
Joint training with complementary tasks (ablation)MLP low-level policy on largest mocap set · Locomotion transfer taskstransfer performanceNo clear effect
Stronger KL regularization on latent embedding (beta) (ablation)MLP low-level policy, latent dimension D=20-60 · Go-to-target transferreward speed and asymptotic returnMixed
Stronger KL regularization on latent embedding (beta=5e-4) (ablation)MLP low-level policy · Walls transfer taskmean returnImproved
Latent space dimensionality D (20 to 60) (ablation)MLP low-level policy · Tracking and transfer taskstracking reward and transfer returnNo clear effect
Separate value function per reward term (ablation)mocap tracking training · Locomotion 40min mocap trackinglearning speedImproved

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