Author's PyTorch implementation of BCQ for continuous and discrete actions.
sfujim/BCQ is ranked 15,290 with 665 stars.
Same-category comparison
sfujim/BCQ is ranked 15,290 among these 8 peers; microsoft/prose is ranked 15,287.
Same-category comparison| Name | Rank | Metrics |
|---|
| M-J-Murray/MAMEToolkit | 15,278 | - Language:
- Python
- Stars:
- 665
- Forks:
- 116
- Description:
- A Python toolkit used to train reinforcement learning algorithms against arcade games.
|
|---|
| google-deepmind/pycolab | 15,283 | - Language:
- Python
- Stars:
- 665
- Forks:
- 123
- Description:
- A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning agents.
|
|---|
| greentfrapp/lucent | 15,284 | - Language:
- Python
- Stars:
- 665
- Forks:
- 95
- Description:
- Lucid library adapted for PyTorch.
|
|---|
| microsoft/prose | 15,287 | - Language:
- C#
- Stars:
- 665
- Forks:
- 101
- Description:
- Microsoft Program Synthesis using Examples SDK is a framework of technologies for the automatic generation of programs from input-output examples. This repo includes samples and sample data for the Microsoft Program Synthesis using Example SDK.
|
|---|
| bingchenlll/FastGAN-pytorch | 15,298 | - Language:
- Python
- Stars:
- 664
- Forks:
- 109
- Description:
- Official implementation of the paper "Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis" in ICLR 2021.
|
|---|
| google-deepmind/searchless_chess | 15,300 | - Language:
- Python
- Stars:
- 664
- Forks:
- 55
- Description:
- Grandmaster-Level Chess Without Search.
|
|---|
| qdrant/quaterion | 15,301 | - Language:
- Python
- Stars:
- 664
- Forks:
- 47
- Description:
- Blazing fast framework for fine-tuning similarity learning models.
|
|---|
| vicariousinc/science_rcn | 15,303 | - Language:
- Python
- Stars:
- 664
- Forks:
- 191
- Description:
- Reference implementation of a two-level RCN model.
|
|---|
Key parameters and specifications
Key parameters and specifications| Parameter | Value |
|---|
| Language | Python |
|---|
| Category | Model Development |
|---|
| Subcategory | Architecture, Reinforcement Learning |
|---|
| Stars | 665 |
|---|
| Forks | 147 |
|---|
| Contributors | 1 |
|---|
| Created date | 2018-12-18 |
|---|
| Updated date | 2026-10-04 |
|---|
| Stars in 1 day | 0 |
|---|
| Stars in 7 days | 0 |
|---|
| Rank | 15,290 |
|---|
| Previous rank | 15,110 |
|---|
| Rank change | -180 |
|---|
| 7-day stars rank | 14,914 |
|---|
| Previous 7-day stars rank | 14,927 |
|---|
| 7-day stars rank change | 13 |
|---|
| Total stars rank | 15,479 |
|---|
| Previous total stars rank | 15,455 |
|---|
| Total stars rank change | -24 |
|---|
| Country | Canada |
|---|
README summary
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.
Frequently asked questions
How many stars and forks are recorded?
sfujim/BCQ has 665 stars and 147 forks.
What is the repository rank?
sfujim/BCQ is ranked 15,290.
What language and category are recorded?
sfujim/BCQ has 665 stars, uses Python and belongs to Model Development.
Which repository is closest in rank?
sfujim/BCQ is compared with microsoft/prose, ranked 15,287 with 665 stars.
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}
}