A compilation of resources I found useful while learning new topics.

I have listed them in the order I used it. Will keep on updating as and when I remember the resources I used.

Contents

• Probabilty, Statistics and Information Theory
• Graph Neural Networks
• Reinforcement Learning
• Multi-agent Reinforcement Learning

Probabilty, Statistics and Information Theory

• Probability course notes by Bruce Hajek
• Lecture notes on Information Theory by Yuri Polyanskiy
• Lecture notes by John Duchi

Graph Neural Networks

• AAAI-19 tutorial on Introduction of Graph Neural Networks
• Blog on node2vec
• Lecture by Jure Leskovec on graph-node embeddings and the corresponding slides
• AAAI-19 Tutorial on graph-node embeddings
• AAAI-19 Tutorial on different types of graph neural networks
• The final part of the above tutorial can be found here
• Python Library for graph neural networks: DGL for practical examples

Reinforcement Learning

• Reinforcement Learning: An Introduction by Sutton and Barto
• Dynamic Programming and Optimal Control by Dimitri Bertsekas
• Introduction to Multi-Armed Bandits by Aleksandrs Slivkins

Multi-agent Reinforcement Learning

• For introduction on MARL
• Survey paper on MARL to get an overview of different algorithms
• AAMAS tutorial on MARL

Implementational stuff

• Tips and Tricks for implementing RL algorithms blog
• Never create a torch.tensor from an existing container of tensors blog
• Using PyTorch + NumPy? You’re making a mistake. blog
• The 32 Implementation Details of Proximal Policy Optimization (PPO) Algorithm blog