Contents of this Repository :
- Discrete Action space games like Pong & Mountain Car with Deep Q Learning (DQN)
- Discrete Action space games like Pong & Mountain Car with vanilla Policy Gradients
- Deep Deterministic Policy Gradients in Continuous Control problems like in MountainCarContinuous-v0 and LunarLanderContinuous-v2 environments.
- Developing a Tic Tac Toe agent using Monte Carlo Tree Search