Welcome in the CartPole-RL directory.
Here you can find python Reinforcement Learning (RL) programs building agents to play cart pole in OpenAI's gym environment, using classical RL algorithms.
At the moment are implemented:
- Deep Q-Learning (DQN)
- SARSA as presented by Sutton and Barto in "Reinforcement Learning: An Introduction"
SARSA(lambda) should be coming next.