HDPG: Hyperdimensional Policy-based Reinforcement Learning for Continuous Control
TimeThursday, July 14th3:50pm - 4:10pm PDT
Location3002, Level 3
AI/ML Design: System and Platform
DescriptionIn this paper, we introduce HDPG, a highly-efficient policy-based RL algorithm using Hyperdimensional Computing (HDC). HDC is a brain-inspired lightweight learning methodology; its holistic representation of information leads to a well-defined set of hardware friendly high-dimensional operations. Our HDPG fully exploits the efficient HDC for high-quality state value approximation and policy gradient update. In our experiments, we use HDPG for robotics tasks with continuous action space and achieve significantly higher rewards compared to DNN-based RL.