|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/deep-reinforcement-learning-made-easy/
课程评论：没有评论
**课程名称:** 深度强化学习入门 (Deep Reinforcement Learning made-easy) **课程概述:** 本课程是深度学习与强化学习的结合，旨在帮助学生理解并掌握深度强化学习的理论与实践。课程将从基础的神经网络（NN）入手，逐步深入到深度神经网络（DNN），包括循环神经网络（RNN）和长短期记忆网络（LSTM）。学生将学习到如何设计自定义的强化学习环境，并将其应用于RL智能体。学完本课程后，学生将能够： * 理解深度学习和强化学习的范式。 * 掌握深度神经网络的架构和优化方法。 * 在TensorFlow中实现深度学习方法并将其应用于数据。 * 理解强化学习的理论基础和算法。 * 将强化学习算法应用于具有复杂动力学的环境。 **课程内容:** * 深度强化学习导论 * 人工神经网络 (ANN) * 从ANN到深度神经网络 (DNN) * 深度学习超参数：正则化 * 深度学习超参数：激活函数与优化 * 卷积神经网络 (CNN) * CNN架构 * 循环神经网络 (RNN) * RNN处理长序列 * LSTM网络 * 马尔可夫决策过程 (MDP) 概述 * 贝尔曼方程与价值函数 * 基于Q-Learning的深度强化学习 * 无模型预测 * 基于策略梯度的深度强化学习 * 强化学习中的探索与利用
This course is the integration of deep learning and reinforcement learning. The course will introduce student with deep neural networks (DNN) starting from simple neural networks (NN) to recurrent neural network and long-term short-term memory networks. NN and DNN are the part of reinforcement learning (RL) agent so the students will be explained how to design custom RL environments and use them with RL agents. After the completion of the course the students will be able:To understand deep learning and reinforcement learning paradigmsTo understand Architectures and optimization methods for deep neural network trainingTo implement deep learning methods within Tensor Flow and apply them to data.To understand the theoretical foundations and algorithms of reinforcement learning.To apply reinforcement learning algorithms to environments with complex dynamics.Course Contents:Introduction to Deep Reinforcement LearningArtificial Neural Network (ANN)ANN to Deep Neural Network (DNN)Deep Learning Hyperparameters: RegularizationDeep Learning Hyperparameters: Activation Functions and OptimizationsConvolutional Neural Network (CNN)CNN ArchitectureRecurrent Neural Network (RNN)RNN for Long SequencesLSTM NetworkOverview of Markov Decision ProcessesBellman Equations and Value FunctionsDeep Reinforcement Learning with Q-LearningModel-Free PredictionDeep Reinforcement Learning with Policy GradientsExploration and Exploitation in Reinforcement Learning
