Repo for holding my implementations of various RL problems.
- FrozenLake.v0 - solutions to the FrozenLake.v0 environment in:
- Numpy
- Keras
- PyTorch
- Policy Gradient with CartPole - solution to the CartPole.v1 environment in PyTorch
- Mountain Car v0 - solutions to OpenAI Mountain Car
- Original
- Modified Reward