CS294-112 深度强化学习 秋季学期(带英语字幕)
来自油管，伯克利大学
伯克利大学的深度强化学习课，因为工作需要用到，看了觉得这门课程很赞
本来不想浪费b站硬盘了，奈何其他上传的同学不传字幕，是可忍孰不可忍？
视频选集
（1/24）
自动连播
1.Introduction and course overview
58:44
2.Supervised learning and imitation
01:22:37
3.Reinforcement learning introduction
01:19:18
4.Policy gradients introduction
01:09:41
5.Actor-critic introduction
01:16:58
6.Value functions introduction
01:07:10
7.Advanced Q-learning algorithms
01:18:03
8.Optimal control and planning
01:14:36
9.Learning dynamical systems from data
01:20:31
10.Learning policies by imitating optimal controllers
01:12:16
11.Advanced model learning and images
01:12:59
12.Connection between inference and control
01:15:58
13.Inverse reinforcement learning
01:14:32
14.Advanced policy gradients (natural gradient, importance sampling)
01:20:10
15.Exploration
01:21:36
16.Exploration (part 2) and transfer learning
01:18:39
17.Multi-task learning and transfer
01:08:35
18.Meta-learning and parallelism
01:16:14
19.Advanced imitation learning and open problems
01:22:35
20.optimization and reinforcement learning in multi-agent settings
01:23:14
21.on the role of entropy and relative entropy in reinforcement
01:23:27
22.deep learning to learn for robotic control
02:22
23.combining reinforcement learning and planning
01:13:25
24.Proximal Policy Optimization and Application
01:16:44
【B站AI论坛】欢迎写代码、做产品的AI开发者发帖加入
共建AI开发者交流地>>
顶部