This is my repo for the course CS3316 Reinforcement Learning of SJTU.
The algorithms of each assignment are listed below:
-
A1: Dynamic Programming
-
A2: Monte-Carlo and Temporal Difference
-
A3: Sarsa and Q-learning
-
A4: Deep Q-learning
-
A5: A3C and DDPG
-
Project: DDPG and DDQN
Honor Code: if you are a student in this course, you are required to finish these algorithms by yourself. The author is not responsible if you copy these codes.