New method uses crowdsourced feedback to help train robots

A new technique enables an AI agent to be guided by data crowdsourced asynchronously from nonexpert human users as it learns to complete a task through reinforcement learning. The method trains the robot faster and better than other approaches.

Related Keywords

Pulkit Agrawal ,Marcel Torne ,Abhishek Gupta ,Improbable Ai Lab ,University Of Washington ,Harvard University ,Watson Ai Lab ,Artificial Intelligence Laboratory ,Department Of Electrical Engineering ,Electrical Engineering ,Computer Science ,Neural Information Processing Systems ,Human Guided Exploration ,Robot Learning ,Pulkit Agarwal ,Reinforcement Learning ,