Skip to content
Rainbow: Combining Improvements in Deep Reinforcement Learning
Python Shell
Branch: master
Clone or download
This branch is 5 commits ahead, 31 commits behind Kaixhin:master.

Latest commit

Fetching latest commit…
Cannot retrieve the latest commit at this time.

Files

Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.idea
experiments
results
.gitignore
LICENSE.md
README.md
agent.py
env.py
environment.yml
experiment3a.sh
experiment3b.sh
gen_baselines.py
gen_figures.py
gen_figures_stacked.py
gradcam.py
main.py
memory.py
misc_functions.py
model.py
requirements.txt
test.py

README.md

Rainbow

MIT License

Rainbow: Combining Improvements in Deep Reinforcement Learning [1].

Results and pretrained models can be found in the releases.

  • DQN [2]
  • Double DQN [3]
  • Prioritised Experience Replay [4]
  • Dueling Network Architecture [5]
  • Multi-step Returns [6]
  • Distributional RL [7]
  • Noisy Nets [8]

Requirements

To install all dependencies with Anaconda run conda env create -f environment.yml and use source activate rainbow to activate the environment.

Available Atari games can be found in the atari-py ROMs folder.

Acknowledgements

References

[1] Rainbow: Combining Improvements in Deep Reinforcement Learning
[2] Playing Atari with Deep Reinforcement Learning
[3] Deep Reinforcement Learning with Double Q-learning
[4] Prioritized Experience Replay
[5] Dueling Network Architectures for Deep Reinforcement Learning
[6] Reinforcement Learning: An Introduction
[7] A Distributional Perspective on Reinforcement Learning
[8] Noisy Networks for Exploration

You can’t perform that action at this time.