This is the code for the paper On Bonus Based Exploration Methods In The Arcade Learning Environment by Adrien Ali Taiga, Williams Fedus, Marlos C. Machado, Aaron Courville and Marc G. Bellemare (2020).
This repository currently includes the following algorithms used in the paper:
- NoisyNetworks (Fortunato et al. 2018)
- Pseudo-counts with PixelCNN (Ostrovski et al. 2017)
- Random Network Distillation (Burda et al. 2019)
python -m bonus_based_exploration.train
--gin_files=configs/dqn_rnd.gin --base_dir=/tmp/dopamine/
You may cite us at
@inproceedings{Taiga2020On, title={On Bonus Based Exploration Methods In The Arcade Learning Environment}, author={Adrien Ali Taiga and William Fedus and Marlos C. Machado and Aaron Courville and Marc G. Bellemare}, booktitle={International Conference on Learning Representations}, year={2020}, url={https://openreview.net/forum?id=BJewlyStDr} }