Skip to content
Projets

sfujim/BCQ has 664 GitHub stars and 147 forks. Star changes are not measured yet. Last checked 2026-11-18 04:55 UTC. Last push 2021-04-06.

Comment ces chiffres sont mesurés

Progression mesurée des étoiles

in 24h
Mise à jour retardée
in 7 days
Mise à jour retardée
in 15 days
Mise à jour retardée
in 1 month
Mise à jour retardée

Variations nettes sur des périodes qui se chevauchent, pas des totaux quotidiens. Les mesures absentes restent vides. Les étoiles indiquent l’intérêt, pas la qualité.

À propos

Author's PyTorch implementation of BCQ for continuous and discrete actions

Apprentissage automatique

README.md

Original

Batch-Constrained Deep Q-Learning (BCQ)

Batch-Constrained deep Q-learning (BCQ) is the first batch deep reinforcement learning, an algorithm which aims to learn offline without interactions with the environment.

BCQ was first introduced in our ICML 2019 paper which focused on continuous action domains. A discrete-action version of BCQ was introduced in a followup Deep RL workshop NeurIPS 2019 paper. Code for each of these algorithms can be found under their corresponding folder.

Bibtex

@inproceedings{fujimoto2019off,
  title={Off-Policy Deep Reinforcement Learning without Exploration},
  author={Fujimoto, Scott and Meger, David and Precup, Doina},
  booktitle={International Conference on Machine Learning},
  pages={2052--2062},
  year={2019}
}
@article{fujimoto2019benchmarking,
  title={Benchmarking Batch Deep Reinforcement Learning Algorithms},
  author={Fujimoto, Scott and Conti, Edoardo and Ghavamzadeh, Mohammad and Pineau, Joelle},
  journal={arXiv preprint arXiv:1910.01708},
  year={2019}
}