sshkhr/rbdoom

RBDoom is a Rainbow-DQN based agent for playing the first-person shooter game Doom

RBDoom

RBDoom is a RAINBOW [1] based agent for playing the first-person shooter game Doom using the VizDoom platform. RAINBOW cmobines various improvements in Deep-Q Learning and demonstrated better overall performance. It is made up of seven components:

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

Requirements

• VizDoom
• Scikit Image
• PyTorch

Acknowledgements

• @Kaixin for Rainbow
• @jaara for AI-blog

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