Notes on Soft Actor-Critic
A short blog post explaining how SAC works. I also implement SAC from scratch and train on a few tasks.
Blog
2021
2019
Notes on DDPG
A short blog post explaining how DDPG works. I also implement DDPG from scratch and train on a few tasks.
2017
Random Walk
I compare different policy evaluation approaches on the random walk problem.
Grid World
Find the shortest path on a grid using RL.