This repository was created to store the work I did for my Professional Elective (Reinforcement Learning)
I continue using this repository for work I do in the field.
Currently I am looking at MuJoCo environments and learning by implementing algorithms such as SARSA, Q-Learning, Policy Gradient methods such as Monte-Carlo REINFORCE and other textbook examples.
I saw two problems - Cart-Pole and Inverted Pendulum, and analyzed how different algorithms improved performance on these.
I am currently learning Multi-Agent RL and am looking forward to doing work in the same.