Demo Notebooks for CSCI 375 Reinforcement Learning


Python Notebooks for In-class demonstration and homeworks in CSCI 375 Reinforcement Learning taught by Professor Mathieu Laurière.

I developed this repository contains course materials for NYU Shanghai’s Fall 2023 CSCI-375 Reinforcement Learning class. The notebooks are mainly used for in-class demonstration and homework. Covered topics are: Multi-armed Bandits, Dynamic Programming, tabular Q-learning, Deep Q-Network, Policy Gradient, Proximal Policy Optimization. The codes and algorithms are following and designed to better demonstrate content in Sutton & Barto’s Reinforcement Learning: An Introduction.

[Code] [Report]