OpenAI Blog · Jul 27, 2017
Better exploration with parameter noise
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
Better exploration with parameter noise. We’ve found that adding adaptive noise to the parameters of reinforcement learning algorithms frequently boosts performance. This exploration method is simple to implement and very rarely decreases performance, so it’s worth trying on any problem. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'Better exploration with parameter noise' affects your current setup before relying on it in production.