Deep Reinforcement Learning (DRL) plays a critical role in controlling future intelligent machines like robots and drones. Constantly retrained by newly arriving real-world data, DRL provides optimal autonomous control solutions for adapting to ever-changing environments. However, DRL repeats inference and training that are computationally expensive on resource-constraint mobile/embedded platforms. Even worse, DRL produces a severe hardware underutilization problem due to its unique execution pattern. To overcome the inefficiency of DRL, we propose Train Early Start , a new execution pattern for building the efficient DRL algorithm. Train Early Start parallelizes the inference and training execution, hiding the serialized performance bottleneck and improving the hardware utilization dramatically. Compared to the state-of-the-art mobile SoC, Train Early Start achieves 1.42x speedup and 1.13x energy efficiency.

中文翻译：

---

通过机器人应用的阶段级并行加速深度强化学习

深度强化学习 (DRL) 在控制机器人和无人机等未来智能机器方面发挥着关键作用。DRL 不断接受新到达的现实世界数据的重新训练，提供最佳的自主控制解决方案，以适应不断变化的环境。然而，DRL 会重复推理和训练，这在资源受限的移动/嵌入式平台上的计算成本很高。更糟糕的是，DRL 由于其独特的执行模式，会产生严重的硬件利用率不足的问题。为了克服 DRL 的低效率，我们建议Train Early Start，一种用于构建高效 DRL 算法的新执行模式。Train Early Start 并行推理和训练执行，隐藏串行化性能瓶颈并显着提高硬件利用率。与最先进的移动SoC相比，Train Early Start 实现了 1.42 倍的加速和 1.13 倍的能源效率。