UC Berkeley深度强化学习课程 by Sergey Levine
http://t.cn/EPetd7X
【UC Berkeley深度强化学习课程】“CS294-112 Fa18 Deep reinforcement learning” by Sergey Levine [UC Berkeley] http://t.cn/RgMJQsV Youtube:http://t.cn/EPetd7X
视频选集
（23/24）
Introduction and Course Overview
01:08:55
Supervised Learning and Imitation
01:20:04
TensorFlow and Neural Nets Review Session
01:18:17
Reinforcement Learning Introduction
01:23:26
Policy Gradients Introduction
01:23:02
Actor-Critic Introduction
01:22:21
Value Functions and Q-Learning
01:12:04
Advanced Q-Learning Algorithms
01:27:01
Advanced Policy Gradients
01:18:33
Optimal Control and Planning
01:26:18
Model-Based Reinforcement Learning
01:19:59
Advanced Model Learning and Images
01:15:08
Learning Policies by Imitating Other Policies
01:26:26
Probability and Variational Inference Primer
01:17:06
Connection between Inference and Control
01:23:45
Inverse Reinforcement Learning
01:11:12
Exploration: Part 1
01:18:19
Exploration: Part 2
01:20:30
Transfer Learning and Multi-Task Learning
01:21:28
Meta-Learning
01:22:20
Parallelism and RL System Design
01:18:39
Advanced Imitation Learning and Open Problems
01:23:06
Guest Lecture: Craig Boutilier
01:23:37
Guest Lecture: Kate Rakelly & Gregory Kahn
01:21:54
顶部