Výsledky vyhledávání - "Kong, Ruofan"

Report

Deep Reinforcement Learning for Dexterous Manipulation with Concept Networks

Autor: Gudimella, Aditya, Story, Ross, Shaker, Matineh, Kong, Ruofan, Brown, Matthew, Shnayder, Victor, Campos, Marcos

Deep reinforcement learning yields great results for a large array of problems, but models are generally retrained anew for each new problem to be solved. Prior learning and knowledge are difficult to incorporate when training new models, requiring i

Externí odkaz: http://arxiv.org/abs/1709.06977