Deep Reinforcement Learning �- 1. Course Overview
Sookyung Kim�sookim@ewha.ac.kr�jh502125@gmail.com
1
Outline
2
Syllabus
3
Syllabus
4
Syllabus
5
Syllabus
6
Resources
7
1. Basic of Reinforcement Learning �
8
1. Basic of Reinforcement Learning �
9
1. Basic of Reinforcement Learning �
Supervised �Learning���
Unsupervised�Learning
Reinforcement�Learning
Semi-sv
10
1. Basic of Reinforcement Learning �
11
1. Basic of Reinforcement Learning �
1. State (observe)
2. Action
3. Reward
I have a Goal!!�Ex: Let’s save the world
Environment � (world)
Agent�(model)
12
1. Basic of Reinforcement Learning �
13
1. Basic of Reinforcement Learning �
���
14
1. Basic of Reinforcement Learning �
15
1. Basic of Reinforcement Learning �
16
1. Basic of Reinforcement Learning �
17
1. Basic of Reinforcement Learning �How to design good RL problem formulation? �- Robot in Room Example�
18
1. Basic of Reinforcement Learning �How to design good RL problem formulation? �- Robot in Room Example�
19
1. Basic of Reinforcement Learning �How to design good RL problem formulation? �- Robot in Room Example�
20
1. Basic of Reinforcement Learning �How to design good RL problem formulation? �- Robot in Room Example�
21
1. Basic of Reinforcement Learning �How to design good RL problem formulation? �- Robot in Room Example�
Lessons from Robot in Room
22
1. Basic of Reinforcement Learning �How to design good RL problem formulation? �- Course runner Example�
Reward Structure may have Unintended Consequences
Player gets reward based on:
23