Ensuring AI works with the right dose of curiosity

A new algorithm makes headway in solving the problem of exploration vs. exploitation in reinforcement learning. Developed by MIT CSAIL researchers, it attempts to make decision-making more efficient.

Related Keywords

United States ,Alison Gopnik ,Zhang Wei Hong ,Eric Chen ,Deepak Pathak ,Pulkit Agrawal ,Joni Pajarinen ,Artificial Intelligence Laboratory ,Carnegie Mellon University ,United States Air Force Artificial Intelligence Accelerator ,Aalto University ,Watson Ai Lab ,Improbable Ai Laboratory ,Army Research Office ,University Of California At Berkeley ,Improbable Ai Lab ,Machine Common Sense Program ,United States Air Force Research Laboratory ,Intelligent Autonomous Systems Group ,Computer Science ,Common Sense Program ,United States Air Force Artificial Intelligence ,Neural Information ,Processing Systems ,Explorations Versus Exploitation Dilemma ,Ecision Making Algorithms ,Reinforcement Learning ,Mit Csail ,Mit Ibm Watson Ai Laboratory ,Mario Kart ,Montezumas Revenge ,Aric Chen ,Lgorithmic Supervision ,