56. Generalization and Safety in Reinforcement Learning and Control: Aviv Tamar - 2
2年前 544观看
加州大学伯克利分校 2017 深度增强学习课程
大学课程 / 社会学
https://www.youtube.com/playlist?list=PLkFD6_40KJIwTmSbCv9OVJB3YaO4sFwkX CS294-112 Deep Reinforcement Learning Sp17 课程主页：http://rll.berkeley.edu/deeprlcourse/
共57集 7.3万人观看
1Introduction and course overview (Levine, Finn, Schulman) - 126:11- 2Introduction and course overview (Levine, Finn, Schulman) - 226:14
- 3Introduction and course overview (Levine, Finn, Schulman) - 326:08
4Supervised learning and decision making (Levine) - 124:06- 5Supervised learning and decision making (Levine) - 224:07
- 6Supervised learning and decision making (Levine) - 324:03
7Optimal control and planning (Levine) - 121:06- 8Optimal control and planning (Levine) - 221:13
- 9Optimal control and planning (Levine) - 321:03
10Learning dynamical system models from data (Levine) - 127:27- 11Learning dynamical system models from data (Levine) - 227:35
- 12Learning dynamical system models from data (Levine) - 327:22
13Learning policies by imitating optimal controllers (Levine) - 123:05- 14Learning policies by imitating optimal controllers (Levine) - 223:08
- 15Learning policies by imitating optimal controllers (Levine) - 322:58
16RL definitions, value iteration, policy iteration (Schulman) - 117:19- 17RL definitions, value iteration, policy iteration (Schulman) - 217:22
- 18RL definitions, value iteration, policy iteration (Schulman) - 317:18
19Reinforcement learning with policy gradients (Schulman) - 121:48- 20Reinforcement learning with policy gradients (Schulman) - 221:54
- 21Reinforcement learning with policy gradients (Schulman) - 321:42
22Learning Q-functions: Q-learning, SARSA, and others (Schulman) - 125:50- 23Learning Q-functions: Q-learning, SARSA, and others (Schulman) - 225:53
- 24Learning Q-functions: Q-learning, SARSA, and others (Schulman) - 325:42
25Advanced Q-learning: replay buffers, target networks, double Q-learning (Sc - 126:47- 26Advanced Q-learning: replay buffers, target networks, double Q-learning (Sc - 226:55
- 27Advanced Q-learning: replay buffers, target networks, double Q-learning (Sc - 326:41
28Advanced topics in imitation and safety (Finn) - 127:53- 29Advanced topics in imitation and safety (Finn) - 227:56
- 30Advanced topics in imitation and safety (Finn) - 327:47
31Inverse RL: acquiring objectives from demonstration (Finn) - 124:47- 32Inverse RL: acquiring objectives from demonstration (Finn) - 224:48
- 33Inverse RL: acquiring objectives from demonstration (Finn) - 324:47
34Advanced policy gradients: natural gradient and TRPO (Schulman) - 128:05- 35Advanced policy gradients: natural gradient and TRPO (Schulman) - 228:08
- 36Advanced policy gradients: natural gradient and TRPO (Schulman) - 328:02
37Policy gradient variance reduction and actor-critic algorithms (Schulman) - 126:55- 38Policy gradient variance reduction and actor-critic algorithms (Schulman) - 227:00
- 39Policy gradient variance reduction and actor-critic algorithms (Schulman) - 326:51
40Summary of policy gradients and temporal difference methods (Schulman) - 124:06- 41Summary of policy gradients and temporal difference methods (Schulman) - 224:10
- 42Summary of policy gradients and temporal difference methods (Schulman) - 323:59
43The exploration problem (Schulman) - 127:18- 44The exploration problem (Schulman) - 227:18
- 45The exploration problem (Schulman) - 327:17
46Parallel RL algorithms, open problems and challenges in deep reinforcement - 126:14- 47Parallel RL algorithms, open problems and challenges in deep reinforcement - 226:22
- 48Parallel RL algorithms, open problems and challenges in deep reinforcement - 326:11
49Transfer in Reinforcement Learning (Finn) - 128:18- 50Transfer in Reinforcement Learning (Finn) - 228:18
- 51Transfer in Reinforcement Learning (Finn) - 328:16
52Neural Architecture Search with Reinforcement Learning: Quoc Le and Barret Z - 125:24- 53Neural Architecture Search with Reinforcement Learning: Quoc Le and Barret Z - 225:29
- 54Neural Architecture Search with Reinforcement Learning: Quoc Le and Barret Z - 325:17
55Generalization and Safety in Reinforcement Learning and Control: Aviv Tamar - 125:39- 56Generalization and Safety in Reinforcement Learning and Control: Aviv Tamar - 225:40
- 57Generalization and Safety in Reinforcement Learning and Control: Aviv Tamar - 325:33
相关视频
03:12这三个书法字，草书不草书，隶书不隶书，您能认出来吗？1月前1421观看
04:23书法之美之《兰亭集序》1年前1569观看
01:03比《兰亭序》更珍贵的书法，是唐代行书之冠，赵孟頫才学到三成2023年5月1日1737观看
01:32颜真卿的一幅“丑书”，笔法直追兰亭，只有书法博士才能看的懂2023年8月12日1719观看
00:18他的隶书在清代誉为“最美”堪称书法奇才。网友：不输《曹全碑》1年前1502观看
01:26书法行草书《告》字的写法1年前1502观看
00:53晋唐的笔法秘诀，被颜真卿点破，学书法一定要弄懂它 #书法欣赏#颜真卿#笔法秘诀1年前1270观看
01:01欧阳询书法《宗》字的写法，上乘的功力，优秀到位！2023年3月1日925观看
01:38“兰亭七子”之一的张利安，书法的风格，王风王韵，米芾的气势5月前1337观看
02:16秋瑾这位女中豪杰的书法，一丝不苟！小楷有魏晋之风，行书则刚劲9月前1346观看
02:42新疆书法大师宋兆敏：篆书雄浑刚劲，笔力遒劲如秦风8月前1422观看
02:03王冬龄书法：小楷承魏晋遗风，草书开启创新之旅4月前1549观看
02:42毛主席的《兰亭序》是一幅草书，他的书法风格非常潇洒，傲视古今6月前1159观看
01:11王羲之“国宝级”行书，失传1000多年，学习晋唐书法，有它就足矣2023年8月27日2170观看
00:40这个书法墙，汇集了我最喜欢的祭侄文稿、兰亭序等旷世奇作，包括张旭、孙过庭等大家的草书作品，汇集了中国...1年前1779观看
01:36陆启成小楷书法：超越欧楷，融合魏晋与文征明风骨，展现刚劲之美5月前1198观看