OpenAI Blog · Oct 31, 2018
Reinforcement learning with prediction-based rewards
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
Reinforcement learning with prediction-based rewards. We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning agents to explore their environments through curiosity, which for the first time exceeds average human performance on Montezuma’s Revenge. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'Reinforcement learning with prediction-based rewards' affects your current setup before relying on it in production.