HDPG
Yang Ni, Mariam Issa, Danny Abraham, Mahdi Imani, Xunzhao Yin, Mohsen Imani
Abstract
Traditional robot control or more general continuous control tasks often rely on carefully hand-crafted classic control methods. These models often lack the self-learning adaptability and intelligence to achieve human-level control. On the other hand, recent advancements in Reinforcement Learning (RL) present algorithms that have the capability of human-like learning. The integration of Deep Neural Networks (DNN) and RL thereby enables autonomous learning in robot control tasks. However, DNN-based RL brings both high-quality learning and high computation cost, which is no longer ideal for currently fast-growing edge computing scenarios.
Topics & Concepts
Computer scienceReinforcement learningAdaptabilityArtificial intelligenceControl (management)Artificial neural networkRobotRobot learningMachine learningMobile robotBiologyEcologyReinforcement Learning in RoboticsFerroelectric and Negative Capacitance DevicesAdvanced Memory and Neural Computing