240
卡斯柏的博客
笔下虽有千言，胸中实无一策

随笔分类 -  增强学习算法

学习笔记 | Morvan - Reinforcement Learning, Part 1: Overview
摘要：Overview 1.1 Why? 1.2 课程要求 4.1 强化学习 (Reinforcement Learning) 4.2 强化学习方法汇总 (Reinforcement Learning) 4.3 什么是 Q Leaning 4.4 什么是 Sarsa 4.5 什么是 Sarsa(lambd 阅读全文
posted @ 2017-01-20 02:23 CasperWin 阅读(203) 评论(0) 推荐(0)
学习笔记 | Morvan - Reinforcement Learning, Part 2: Q-learning
摘要：Q-learning 2.1 小例子 2.2 Q-learning 算法更新 2.3 Q-learning 思维决策 Auxiliary Material A Painless Q-Learning Tutorial Simple Reinforcement Learning with Tensor 阅读全文
posted @ 2017-01-19 07:26 CasperWin 阅读(438) 评论(0) 推荐(0)
学习笔记 | UCL Course on RL
摘要：Lecture 1 Video: https://www.youtube.com/watch?v=2pWv7GOvuf0 Slide: Introduction to Reinforcement Learning Key points: 1. An RL agent may include one 阅读全文
posted @ 2017-01-18 09:32 CasperWin 阅读(528) 评论(0) 推荐(0)
学习笔记 | Morvan - Reinforcement Learning, Part 4: Deep Q Network
摘要：Deep Q Network 4.1 DQN 算法更新 4.2 DQN 神经网络 4.3 DQN 思维决策 4.4 OpenAI gym 环境库 Deep Q Network 的简称叫 DQN, 是将 Q learning 的优势 和 Neural networks 结合了. Notes Psudo 阅读全文
posted @ 2017-01-18 05:08 CasperWin 阅读(523) 评论(0) 推荐(0)
学习笔记 | CMU 10703: Deep Reinforcement Learning and Control, Spring 2017
摘要：Homepage Warm up First Chapters from Reinforcement Learning: an Introduction, Sutton&Barto ,Second Edition (pdf) & also ebook here Dave Silver’s cours 阅读全文
posted @ 2017-01-18 03:14 CasperWin 阅读(1364) 评论(0) 推荐(0)
学习笔记 | Morvan - Reinforcement Learning, Part 3: Sarsa
摘要：Sarsa 什么是Sarsa 什么是Sarsa (lamda) 3.1 Sarsa 算法更新 3.2 Sarsa 思维决策 3.3 Sarsa-lambda Notes What is Sarsa? From Wikipedia: State-Action-Reward-State-Action ( 阅读全文
posted @ 2017-01-14 07:10 CasperWin 阅读(397) 评论(0) 推荐(0)