- python3.6
- gym
- OpenCV Python
- PyTorch
- tensorboardX
- atari roms
Modify the parameters in config.conf
.
python train.py
In a separate terminal:
tensorboard --logdir runs
python eval.py
[1] Actor-Critic Algorithms
[2] Efficient Parallel Methods for Deep Reinforcement Learning
[3] Curiosity-driven Exploration by Self-supervised Prediction
[4] Proximal Policy Optimization Algorithms
[5] Large-Scale Study of Curiosity-Driven Learning