trends.barnas.net

method · first seen 27 Oct 2026

asymmetric actor-critic

Also: privileged critic

Reinforcement learning setup where the critic uses privileged simulator information while the actor uses only deployable observations.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

humanoid parkourmaximum-entropy reinforcement learningobservation delay in reinforcement learning