OpenAI Blog · Mar 20, 2018
Variance reduction for policy gradient with action-dependent factorized baselines
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
Variance reduction for policy gradient with action-dependent factorized baselines. Source details are limited, so this entry summarizes the headline change only for operators tracking their tools.
Operator takeaway: For operators: review whether 'Variance reduction for policy gradient with action-dependent factorized baselines' affects your current setup before relying on it in production.