Title

第17講 Deep Reinforcement Learning/ DQN & Policy Network

Video

L17I

Syllabus

章節大綱

L17_A
        Introduction
 
L17_B
        Deep Q-Network (DQN)
 
L17_C
        Double DQN
 
L17_D
        Prioritized Reply
 
L17_E
        Dueling Network
 
L17_F
        NoisyNet and Scalable Implementations (e.g.
        Google Gorila)
 
L17_G
        Policy Gradient Methods & DDPG
 
L17_H
        Episodic Policy Gradient & REINFORCE
 
L17_I
        Reducing Variance
 
L17_J
        Baseline Subtraction
 
L17_K
        Function Approximation Actor-Critic and A3C