论文标题
平衡卡特柱系统与增强学习 - 教程
Balancing a CartPole System with Reinforcement Learning -- A Tutorial
论文作者
论文摘要
在本文中，我们提供了实施各种强化学习（RL）算法来控制卡车杆系统的详细信息。特别是，我们描述了各种RL概念，例如Q学习，深Q网络（DQN），双DQN，决斗网络，（优先）经验重播并显示了它们对学习绩效的影响。在此过程中，读者将被介绍给OpenAI/Gym和用于实施上述概念的Keras实用程序。据观察，DQN具有PER，在所有其他架构中都能在150集中解决该问题的所有其他体系结构提供最佳性能。
In this paper, we provide the details of implementing various reinforcement learning (RL) algorithms for controlling a Cart-Pole system. In particular, we describe various RL concepts such as Q-learning, Deep Q Networks (DQN), Double DQN, Dueling networks, (prioritized) experience replay and show their effect on the learning performance. In the process, the readers will be introduced to OpenAI/Gym and Keras utilities used for implementing the above concepts. It is observed that DQN with PER provides best performance among all other architectures being able to solve the problem within 150 episodes.
