ELEC-E8125 Reinforcement Learning
Content
Markov Decision Processes
Reading: (Sutton and Barto 2018) Chapter 2-2.3, 2.5-2.6, 3-3.8.
Value-based methods in discrete domains
Reading: (Sutton and Barto 2018) Chapter 5-5.4, 5.6, 6-6.5.
Function approximation
Reading: (Sutton and Barto 2018) Chapter 9-9.3, 10-10.1.
Policy gradient
Reading: (Sutton and Barto 2018) Chapter 13-13.3
Actor-critic
Reading: (Sutton and Barto 2018) Chapter 13.5, 13.7.
Optimal control
Model-based Reinforcement Learning
Reading: (Sutton and Barto 2018) Chapter 8-8.2.
Partially Observable Markov Decision Processes
Reading: (Cassandra 2003) From "Brief Introduction to MDPs" to "General Form of a POMDP solution".