|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/deep-q-learning-from-paper-to-code/
课程评论：没有评论
**课程名称：** 现代强化学习：深度Q学习代理 (PyTorch & TF2) **课程概述：** 本课程是一门全面的深度强化学习课程，旨在教授一种可重复的框架，用于阅读和实现深度强化学习的研究论文。学员将深入学习并实践经典的深度Q学习（DQN）、双重深度Q学习（DDQN）和对偶深度Q学习（Dueling DQN）算法。课程将指导学员使用Pythonic且简洁的PyTorch和TensorFlow 2代码来实现这些算法，并鼓励学员将其扩展到未来任何新的深度Q学习算法。 学员将利用这些算法来解决OpenAI Gym的Atari库中的各种环境，包括 Pong、Breakout和Bankheist等经典游戏。课程的重点在于教授如何修改OpenAI Gym的Atari库以满足原始深度Q学习论文中的具体要求，这是成功实现这些算法的关键。具体学习内容包括： * **行动重复：** 减少计算开销。 * **Atari屏幕图像重新缩放：** 提高效率。 * **帧堆叠：** 赋予深度Q代理运动感知能力。 * **评估代理性能：** 通过随机无操作（no-ops）来处理模型过拟合。 * **奖励裁剪：** 使深度Q学习代理能够泛化到不同得分尺度的Atari游戏。 **先修知识：** 即使没有强化学习或深度强化学习的经验，本课程也无需担心。课程包含一个完整的、简洁的强化学习基础知识介绍，将以解决OpenAI Gym的Frozen Lake环境为例进行讲解。内容涵盖： * 马尔可夫决策过程（MDP） * 时间差学习（TD Learning） * 原始Q学习算法 * 求解贝尔曼方程（Bellman Equation） * 价值函数（Value Functions）和动作价值函数（Action-Value Functions） * 无模型 vs. 有模型强化学习（Model-free vs. Model-based RL） * 探索-利用困境（Explore-Exploit Dilemma）的解决方案，包括乐观初始值（Optimistic Initial Values）和epsilon-greedy动作选择。 此外，课程还包含一个使用PyTorch框架的深度学习迷你课程。该部分面向熟悉深度学习基本概念但对具体实现不熟悉，或熟悉其他深度学习框架（如TensorFlow或Keras）的学员。学员将学习如何使用PyTorch编写深度神经网络，以及卷积神经网络（CNN）的工作原理。这些知识将被用于实现一个简单的深度Q学习代理，以解决OpenAI Gym的Cartpole问题。
In this complete deep reinforcement learning course you will learn a repeatable framework for reading and implementing deep reinforcement learning research papers. You will read the original papers that introduced the Deep Q learning, Double Deep Q learning, and Dueling Deep Q learning algorithms. You will then learn how to implement these in pythonic and concise PyTorch and Tensorflow 2 code, that can be extended to include any future deep Q learning algorithms. These algorithms will be used to solve a variety of environments from the Open AI gym's Atari library, including Pong, Breakout, and Bankheist. You will learn the key to making these Deep Q Learning algorithms work, which is how to modify the Open AI Gym's Atari library to meet the specifications of the original Deep Q Learning papers. You will learn how to:Repeat actions to reduce computational overheadRescale the Atari screen images to increase efficiencyStack frames to give the Deep Q agent a sense of motionEvaluate the Deep Q agent's performance with random no-ops to deal with model over trainingClip rewards to enable the Deep Q learning agent to generalize across Atari games with different score scalesIf you do not have prior experience in reinforcement or deep reinforcement learning, that's no problem. Included in the course is a complete and concise course on the fundamentals of reinforcement learning. The introductory course in reinforcement learning will be taught in the context of solving the Frozen Lake environment from the Open AI Gym. We will cover:Markov decision processesTemporal difference learningThe original Q learning algorithmHow to solve the Bellman equationValue functions and action value functionsModel free vs. model based reinforcement learningSolutions to the explore-exploit dilemma, including optimistic initial values and epsilon-greedy action selectionAlso included is a mini course in deep learning using the PyTorch framework. This is geared for students who are familiar with the basic concepts of deep learning, but not the specifics, or those who are comfortable with deep learning in another framework, such as Tensorflow or Keras. You will learn how to code a deep neural network in Pytorch as well as how convolutional neural networks function. This will be put to use in implementing a naive Deep Q learning agent to solve the Cartpole problem from the Open AI gym.
