OpenAI Blog · Oct 11, 2017
Meta-learning for wrestling
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
Meta-learning for wrestling. We show that for the task of simulated robot wrestling, a meta-learning agent can learn to quickly defeat a stronger non-meta-learning agent, and also show that the meta-learning agent can adapt to physical malfunction. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'Meta-learning for wrestling' affects your current setup before relying on it in production.