AI Paper Atlas

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

Continual Learning of Control Primitives : Skill Discovery via Reset-Games

Kelvin Xu, Siddharth Verma, Chelsea Finn, Sergey Levine

NeurIPS 2020 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Intrinsically motivated exploration · 3 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 multiple resetter skills (reset game with diversity bonus) instead of a single adversary (ablation)LSR · DClaw-ManipulateFreeObjectreset-free performanceImproved
remove the diversity bonus (Multiple-Resetters variant) (ablation)LSR · DClaw-ManipulateFreeObjectreset-free performanceHurt
use LSR instead of R3L perturbation controllerreset-free learning · DClaw-ManipulateFreeObjectiterations to converge: ~28.6% fasterImproved
use an explicit reset policy instead of reset skill gamereset-free learning · DClaw-ManipulateFreeObjectperformanceHurt
use LSR skills instead of DIAYN and DADS skillshierarchical controller · Ant-MediumMazenormalized returnImproved
use LSR skills instead of DIAYN and DADS skillshierarchical controller · Ant-Waypointsnormalized returnImproved
use (x,y) prior state representationDIAYN and DADS · Ant skill learningskill qualityMixed

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