[返回課程頁面]
第17講 Deep Reinforcement Learning/ DQN & Policy Network
課程影音
L17A
L17A
Introduction
L17B
Deep Q-Network (DQN)
L17C
Double DQN
L17D
Prioritized Reply
L17E
Dueling Network
L17F
NoisyNet and Scalable Implementations (e.g.
Google Gorila)
L17G
Policy Gradient Methods & DDPG
L17H
Episodic Policy Gradient & REINFORCE
L17I
Reducing Variance
L17J
Baseline Subtraction
L17K
Function Approximation Actor-Critic and A3C
Introduction
L17B
Deep Q-Network (DQN)
L17C
Double DQN
L17D
Prioritized Reply
L17E
Dueling Network
L17F
NoisyNet and Scalable Implementations (e.g.
Google Gorila)
L17G
Policy Gradient Methods & DDPG
L17H
Episodic Policy Gradient & REINFORCE
L17I
Reducing Variance
L17J
Baseline Subtraction
L17K
Function Approximation Actor-Critic and A3C