Course Schedule

Weekday Regular Schedule

Group	Type	Hours	Location
All	Lecture	Wednesday 10:00-13:00	Dan David 001
1	Recitation	Wednesday 14:00-15:00	Melamed
2	Recitation	Wednesday 15:00-16:00	Melamed

Detailed Schedule

Lecture	Date	Topics	Lecture Slides	Recitation Slides	Comments
1	27/2/2019	Introduction	lecture 1 scribe 1	Pytorch recitation 1
2	6/3/2019	Deterministic Decision Processes: Finite Horizon and Average cost	lecture 2 scribe 2	recitation 2	(extra) exercises
3	13/3/2019	Markov Chains and Markov Decision Processes: Finite Horizon	lecture 3 scribe 3	recitation 3
4	20/3/2019	MDP: discounted infinite horizon	lecture 4 scribe 4	recitation 4 slides	(extra) exercises
5	27/3/2019	Model based learning: off-policy, on-policy, Rmax	lecture 5 scribe 5	recitation 5 slides
6	3/4/2019	Model free learning: Q-learning, SARSA, Monte-Carlo	lecture 6 scribe 6	recitation 6
7	10/4/2019	Model free learning: TD(0), TD(lambda), Importance Sampling, Action-Critic	lecture 7 scribe 7	recitation 7
8	1/5/2019	Value Function Approximation	lecture 8 scribe 8	recitation 8
9	15/5/2019	Policy Gradient	lecture 9 scribe 9	recitation 9 code
10	22/5/2019	Stochastic Multi-Arm Bandits	lecture 10 scribe 10	recitation 10
11	29/5/2019	Partially Observable MDP (POMDP)	lecture 11 scribe 11	recitation 11
12	5/6/2019	Linear Dynamics models (LQR)	lecture 12 scribe 12	recitation 12
13	12/6/2019	Generative model; Inverse RL	lecture 13 scribe 13	recitation 13