Random Network Distillation
January 5, 2019 ยท View on GitHub
Intrinsic Reward Graph with play
| Venture | Montezuma's Revenge |
|---|---|
 |  |
| ~ | New model for Montezuma |
- Advantage Actor critic [1]
- Parallel Advantage Actor critic [2]
- Exploration by Random Network Distillation [3]
- Proximal Policy Optimization Algorithms [4]
1. Setup
Requirements
- python3.6
- gym
- OpenCV Python
- PyTorch
- tensorboardX
2. How to Train
Modify the parameters in config.conf as you like.
python train.py
3. How to Eval
python eval.py
4. Loss/Reward Graph
- Montezuma's Revenge Env
- Venture Env
References
[1] Actor-Critic Algorithms
[2] Efficient Parallel Methods for Deep Reinforcement Learning
[3] Exploration by Random Network Distillation
[4] Proximal Policy Optimization Algorithms