Deep reinforcement learning (DRL) has been demonstrated to provide promising results in several challenging decision making and control tasks. However, the required inference costs of deep neural networks (DNNs) could prevent DRL from being applied to mobile robots which cannot afford high energy-consuming computations. To enable DRL methods to be affordable in such energy-limited platforms, we propose an asymmetric architecture that reduces the overall inference costs via switching between a computationally expensive policy and an economic one. The experimental results evaluated on a number of representative benchmark suites for robotic control tasks demonstrate that our method is able to reduce the inference costs while retaining the agent's overall performance.
翻译:深层强化学习(DRL)已证明为若干具有挑战性的决策和控制任务提供了有希望的结果,然而,深神经网络(DNNs)所需的推断成本可以防止DRL被应用于负担不起高耗能计算成本的移动机器人。为了使DRL方法在这种能源有限的平台上能够负担得起,我们建议建立一个不对称结构,通过在计算昂贵的政策与经济政策之间转换来降低总体推论成本。一些具有代表性的机器人控制任务基准套件的实验结果表明,我们的方法能够降低推论成本,同时保留代理人的总体性能。