Efficient Off-Policy Reinforcement Learning via Brain-Inspired Computing
This work addresses efficiency challenges in reinforcement learning for real-time applications, though it appears incremental as it builds on existing off-policy methods with a novel lightweight model.
The paper tackles the high computational cost of modern reinforcement learning algorithms like DQN by proposing QHD, a brain-inspired off-policy method that achieves up to 34.6 times speedup while providing comparable or higher rewards on desktop and embedded platforms.
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 real-time 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 significantly better overall efficiency than DQN while providing higher or comparable rewards. QHD is also suitable for highly-efficient reinforcement learning with great potential for online and real-time learning. Our solution supports a small experience replay batch size that provides 12.3 times speedup compared to DQN while ensuring minimal quality loss. Our evaluation shows QHD capability for real-time learning, providing 34.6 times speedup and significantly better quality of learning than DQN.