Machine Learning II
Value Methods in RL
1
Ken Q. Pu, Associate Professor in Computer Science
Faculty of Science, Ontario Tech University
Basic Definitions
2
Basic Definitions
3
Basic Definitions
4
Return
5
Expected Return of a Policy & Optimal Policy
6
Evaluating States and Actions With Value Functions
7
Evaluating States and Actions With Value Functions
8
Check Your Understanding
9
From Optimal Action-Value Function To Policy
10
Bellman Equations for On Policy Value Functions
11
Bellman Equations for Optimal Value Functions
12
Value Iteration
13
Value Iteration
14
Temporal Difference Learning (TD)
15
Q-Learning
16
Q-Learning
17
Deep Q-Learning Network (DQN)
18
DQN
19
DQN
20
DQN: Experience Buffer & Experience Replay
21
DQN: Target and Policy DQN
22
Atari DQN 2013
23
More About DQN
24