Efficient Off-Policy Reinforcement Learning via Brain-Inspired Computing

Reinforcement Learning (RL) has opened up new opportunities to enhance existing smart systems that generally include a complex decision-making process. However, modern RL algorithms, e.g., Deep Q-Networks (DQN), are based on deep neural networks, resulting in high computational costs. In this paper, we propose QHD, an off-policy value-based Hyperdimensional Reinforcement Learning, that mimics brain properties toward robust and realtime learning. QHD relies on a lightweight brain-inspired model to learn an optimal policy in an unknown environment. On both desktop and power-limited embedded platforms, QHD achieves signiffcantly better overall effciency than DQN while providing higher or comparable rewards. QHD is also suitable for highlyeffcient reinforcement learning with great potential for online and real-time learning. Our solution supports a small experience replay batch size that provides 12.3x speedup compared to DQN while ensuring minimal quality loss. Our evaluation shows QHD capability for real-time learning, providing 34.6x speedup and signiffcantly better quality of learning than DQN.