README.md

Reinforcement.Learning

Contributions are welcome

Progress

1. • Deep Q Network
2. • Dueling Q Network
3. • Policy Gradient: REINFORCE
4. • Advantage Actor-Critic
5. • Deep Deterministic Policy Gradient

TODO

1. • Asynchronous Advantage Actor-Critic (A3C)
2. • Estimate the concrete performance of each algorithms

Licence

MIT Licence