Skip to content

This is a python JAX implementation of the paper: Rainbow: Combining improvements in deep reinforcement learning, by M. Hessel et al. In Thirty-Second AAAI Conference on Artificial Intelligence.

License

Notifications You must be signed in to change notification settings

epignatelli/rainbow-drl

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Project Status: WIP – Initial development is in progress, but there has not yet been a stable, usable release suitable for the public. License: MIT

Rainbow: Combining Improvements in Deep Reinforcement Learning

This is a jax implementation of the paper: Hessel, M., Modayil, J., Van Hasselt, H., Schaul, T., Ostrovski, G., Dabney, W., Horgan, D., Piot, B., Azar, M. and Silver, D., 2018, April. Rainbow: Combining improvements in deep reinforcement learning. In Thirty-Second AAAI Conference on Artificial Intelligence.

Please, feel free to raise issues to ask questions or flag flaws and mistakes in the implementation.
Should you find this useful for you, I would be grateful if you'd star⭐ it :)

Roadmap:

  • DQN (Deep Q-Network)
  • DDQN (Double Deep Q-Network)
  • Prioritized DDQN (Prioritized experience replay)
  • Dueling DDQN
  • Multi-step learning
  • A3C (Asynchronous Advantage Actor Critic)
  • Distributional DQN
  • Noisy DQN
  • Multi-

About

This is a python JAX implementation of the paper: Rainbow: Combining improvements in deep reinforcement learning, by M. Hessel et al. In Thirty-Second AAAI Conference on Artificial Intelligence.

Topics

Resources

License

Stars

Watchers

Forks