Lecture 7��Deep Deterministic Policy Gradient (DDPG) Method
1
Instructor: Ercan Atam
Institute for Data Science & Artificial Intelligence
Course: DSAI 642- Advanced Reinforcement Learning
2
List of contents for this lecture
3
Relevant readings/videos for this lecture
(Some slides are modified/improved versions from here)
(very good and detailed lecture on DDPG!)
4
What is the DDPG method?
5
The intuition behind the DDPG method
6
Generalizing DQN to continuous actions (1)
7
Generalizing DQN to continuous actions (2)
}
8
From DQN to DDPG
9
The Q-Learning side of the DDPG method (1)
10
The Q-Learning side of the DDPG method (2)
11
The policy learning side of DDPG (1)
12
The policy learning side of DDPG (2)
13
The policy learning side of DDPG (3)
14
Exploration-Exploitation in the DDPG method
15
DDPG algorithm
16
DDPG algorithm explained visually
17
+s, -s
18
Summary
References �(utilized for preparation of lecture notes or MATLAB code)
19