Tentative Class Schedule

All the lecture scribbles can be found here.

Lec Date Instructor Topic Mandatory Readings Optional Readings
1 26 Aug 2024 Sarath Chandar Introduction to Reinforcement Learning, Sequential Decision Problems Logistics and Intro Slides, Sutton and Barto Chapter 01, Reward is Enough, Scalar Reward is Not Enough, Faulty Reward Functions Computing Machinery and Intelligence by Alan Turing,
Probability Review,
Linear Algebra Review
2 09 Sep 2024 Sarath Chandar Immediate Reinforcement Learning and Multi-armed Bandits Sutton and Barto Chapter 02, Proof of UCB1’s regret bound by Ann He and Jeremy Kun 3 lectures on UCB1 by Prof. Balaraman Ravindran: UCB1, Concentration Bounds, UCB Regret Bound
3 16 Sep 2024 Nishanth Anand Markov Decision Process and Dynamic Programming Sutton and Barto Chapter 03 and Chapter 04  
4 23 Sep 2024 Nishanth Anand Monte-Carlo Methods Sutton and Barto Chapter 05  
5 01 Oct 2024 Nishanth Anand Temporal Difference (TD) Learning - I    
6 07 Oct 2024 Nishanth Anand Temporal Difference (TD) Learning - II    
7 21 Oct 2024 Sarath Chandar Function Approximation - I    
  25 Oct 2024   Mid-Term Exam    
8 28 Oct 2024 Sarath Chandar Function Approximation - II    
9 04 Nov 2024 Sarath Chandar Policy Gradients    
10 11 Nov 2024 Sarath Chandar Natural Policy Gradients    
11 18 Nov 2024 Sarath Chandar Determistic Policy Gradients    
12 25 Nov 2024 Sarath Chandar Model-based RL    
13 02 Dec 2024 Sarath Chandar Frontiers in RL    

Tutorials

Lec Date Time Topic Lecture Videos Lecture Materials
1 30 Aug 2024   No lab. Use the lab time for reading.    
2 06 Sep 2024   No lab. Use the lab time for reading.    
3 13 Sep 2024        
4 20 Sep 2024        
5 27 Sep 2024        
6 04 Oct 2024        
7 11 Oct 2024        
8 25 Oct 2024        
9 01 Nov 2024        
10 08 Nov 2024        
11 15 Nov 2024        
12 22 Nov 2024        
13 29 Nov 2024