Deep Reinforcement Learning

Published on Jul 27, 201753399 Views

DLSS & RLSS 2017 - Montreal

Deep reinforcement learning00:00

History00:27

Artificial intelligence01:43

Reinforcement learning03:47

Reinforcement learning - 105:28

Reinforcement learning - 208:00

Approaches to reinforcement learning08:59

Reinforcement learning - 311:32

Deep reinforcement learning13:57

Deep Q Networks15:53

Q-learning16:15

Q-learning - 122:49

DQN23:33

DQN - 128:14

DQN - 231:54

Target Network Intuition37:26

Experience replay43:58

DQN - 344:52

Experience replay - 145:02

Prioritized Experience Replay46:25

Double DQN55:03

Double DQN - 157:18

Double DQN - 257:48

Double DQN - 358:27

Double DQN - 458:37

Insights01:05:47

Dueling DQN01:07:15

Policy Gradient01:15:02

Contextual Bandit Policy Gradient01:16:19

Policy Gradient Theorem01:16:25

Variance Reduction01:17:03

AsyncRL01:18:36

Async Advantage Actor-Critic (A3C)01:20:10