Assignments of DSE 302. A course on reinforcement learning.
Here I have stored all of my RL assignments. All of these tested being able to implement the algorithms taught (Greedy, Epsilon greedy, Upper Confidence Bound, Optimistic Intial values, Gradient bandits), making evironments, and applying various complex RL algorithms on them (On-Policy Monte Carlo, Off-Policy Monte Carlo, On-Policy TD Control (SARSA), Off-Policy TD Control (Q-Learning), Policy Gradient Method). It was a fun journey of realising a few nuances to be taken care of when implementing. It has given me a lot more confidence in my ability to understand and code out full fledged environments and apply the RL algorithms on them.