Distillation Strategies for Proximal Policy Optimization

Understand

Vision-based deep reinforcement learning (RL) typically obtains performance benefit by using high capacity and relatively large convolutional neural networks (CNN).

• However, a large network leads to higher inference costs (power, latency, silicon area, MAC count).
• Many inference optimizations have been developed for CNNs.
• Some optimization techniques offer theoretical efficiency, such as sparsity, but designing actual hardware to support them is difficult.