DQN 뿌수기

Value based RL의 Baseline 인 DQN을 완벽히 이해하고,
나아가서 더 빠르고, 효율적으로 학습할 수 있는 개선점을 찾아서 적용하는 프로젝트.

• DQN [2] (모두)
• Double DQN [3] (김준태님)
• Prioritised Experience Replay [4] (박민철님)
• Dueling Network Architecture [5] (김상근님)
• Multi-step Returns [6] (이건희님)
• Distributional RL [7]
• Noisy Nets [8] (주찬웅님)

1. Setup

Requirements

---

• atari-py
• OpenCV Python
• Plotly
• PyTorch

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

2. How to Train

3. How to Eval

4. Loss/Reward Graph

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