Combining improvements in deep reinforcement learning. Results and pretrained models can be found in the releases. Data-efficient Rainbow can be run using several options (note that the "unbounded" memory is implemented here in practice by manually setting the memory capacity to be the same as the maximum number of timesteps).
Features
- Prioritised Experience Replay
- Dueling Network Architecture
- Multi-step Returns
- Run the original Rainbow with the default arguments
- Requires atari-py
- Requires OpenCV Python
Categories
Machine LearningLicense
MIT LicenseFollow Rainbow
You Might Also Like
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Rainbow!