Applying reinforcement learning to environments with sparse and underspecified rewards is an ongoing challenge, requiring generalization from limited feedback. See how we address this with a novel method that provides more refined feedback to the agent. https://t.co/PdjltHbgbH

Favorite tweet:

Applying reinforcement learning to environments with sparse and underspecified rewards is an ongoing challenge, requiring generalization from limited feedback. See how we address this with a novel method that provides more refined feedback to the agent. https://t.co/PdjltHbgbH

— Google AI (@GoogleAI) February 22, 2019

Applying reinforcement learning to environments with sparse and underspecified rewards is an ongoing challenge, requiring generalization from limited feedback. See how we address this with a novel method that provides more refined feedback to the agent. https://t.co/PdjltHbgbH http://twitter.com/GoogleAI/status/1099025199909953536 https://t.co/PdjltHbgbH February 23, 2019 at 04:16AM