
10703 (Spring 2018): Deep RL and Control
 Lecture Schedule
Tentative Lecture Schedule
 Jan 17, Introduction [pdf]
Reading: Sutton & Barto, Chapters 1,2
 Jan 22, Markov decision processes (MDPs)
[pdf]
Reading: Sutton & Barto, Chapter 3
 Jan 24, Solving known MDPs: Dynamic Programming [pdf]
Reading: Sutton & Barto, Chapter 4
 Jan 29, Monte Carlo learning
[pdf]
Reading: Sutton & Barto, Chapter 5
 Jan 31, Temporal difference learning
[pdf]
Reading: Sutton & Barto, Chapter 6
 Feb 5, VF approximation, MC, TD with VF approximation.
[pdf]
Reading: Sutton & Barto, Chapter 9
 Feb 7, VF approximation, Deep Learning, Neural Nets.
[pdf]
Reading: Deep Learning book, GBC, Chapter 6
 Feb 12, VF approximation, Deep Learning, Convnets, Optimization.
[pdf]
Reading: Deep Learning book, GBC, Chapter 9
 Feb 14, Deep QLearning, Double QLearning, Replay Memory
[pdf]
Reading: Relevant papers (see lecture slides)
 Feb 19, Monte carlo tree search
[pdf]
Reading: Sutton & Barto, Chapter 8
 Feb 20, Feb 26, Policy Gradient I, Policy Gradient II
[pdf], [pdf]
Reading: Sutton & Barto, Chapter 13
 Feb 28, Continuous Actions, Variational Autoencoders, multimodal stochastic policies
[pdf]
Reading: Deep Learning book, GBC, Chapter 20.10
 March 5, No class
 March 7, Imitation Learning I: Behavior Cloning, DAGGER,
Structured Prediction
[pdf]
Reading:
 March 1214, Spring Break
 March 19, Imitation Learning II: Inverse RL, MaxEnt IRL
[pdf]
Reading:
 March 21, Optimal control, trajectory optimization
[pdf]
Reading:
 March 26, Guest Lecture
 March 28, Optimal control, trajectory optimization, part II
[pdf]
Reading:
 April 2, 4, Learning Local models, TRPO, Imitating Optimal Controllers
[pdf]
Reading:
 April 9,11 Endtoend Model Based Reinforcement Learning
[pdf]
Reading:
 April 16, Guest Lecture
 April 16, Exploration and Exploitation
[pdf]
Reading: Sutton & Barto, Chapter 2
 April 23, Student Project Presentations
 April 25, Hierarchical RL and Tranfer Learning
[pdf]
 April 30, Memory Augmented RL
[pdf]
[
Home 
Assignments 
Lecture Schedule 
]
10703 (Spring 2018): Deep RL and Control
 http://www.cs.cmu.edu/~rsalakhu/10703/
