Science Score: 67.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 4 DOI reference(s) in README -
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (6.6%) to scientific vocabulary
Repository
JAX implementation of Real Time Recurrent Learning
Basic Info
Statistics
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
jax-rtrl
Fast implementation of Real-Time Recurrent Learning (RTRL) [1] and Random Feedback Local Online (RFLO) Learning [2] for Continuous Time Recurrent Neural Networks [3] and Linear Recurrent Units [4] in flax.
Work in progress!
If you found this repository useful in your research, please consider citing the following paper:
bibtex
@article{lemmel2024,
title = {Real-Time Recurrent Reinforcement Learning},
author = {Lemmel, Julian and Grosu, Radu},
year = {2024},
month = mar,
url = {http://arxiv.org/abs/2311.04830},
doi = {10.48550/arXiv.2311.04830},
urldate = {2024-04-03},
}
[1] R. J. Williams and D. Zipser, “A Learning Algorithm for Continually Running Fully Recurrent Neural Networks,” Neural Computation, vol. 1, no. 2, pp. 270–280, Jun. 1989, doi: 10.1162/neco.1989.1.2.270.
[2] J. M. Murray, “Local online learning in recurrent networks with random feedback,” eLife, vol. 8, p. e43299, May 2019, doi: 10.7554/eLife.43299.
[3] K. Funahashi and Y. Nakamura, “Approximation of dynamical systems by continuous time recurrent neural networks,” Neural Networks, vol. 6, no. 6, pp. 801–806, Jan. 1993, doi: 10.1016/S0893-6080(05)80125-X.
[4] N. Zucchet, R. Meier, S. Schug, A. Mujika, and J. Sacramento, “Online learning of long-range dependencies,” in Thirty-seventh Conference on Neural Information Processing Systems, Nov. 2023.
Owner
- Name: Julian Lemmel
- Login: FranzKnut
- Kind: user
- Repositories: 1
- Profile: https://github.com/FranzKnut
Citation (CITATION.cff)
cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: Lemmel
given-names: Julian
orcid: https://orcid.org/0000-0002-3517-2860
title: "Real-Time Recurrent Reinforcement Learning"
version: 0.1.0
identifiers:
- type: doi
value: 10.48550/arXiv.2311.04830
date-released: 2024
GitHub Events
Total
- Watch event: 1
- Public event: 1
- Push event: 39
Last Year
- Watch event: 1
- Public event: 1
- Push event: 39
Dependencies
- absl-py 2.2.1
- attrs 25.3.0
- chex 0.1.89
- cloudpickle 3.1.1
- colorama 0.4.6
- dacite 1.9.2
- decorator 5.2.1
- distrax 0.1.5
- dm-tree 0.1.9
- docstring-parser 0.16
- etils 1.12.2
- flax 0.10.4
- fsspec 2025.3.0
- gast 0.6.0
- humanize 4.12.2
- importlib-resources 6.5.2
- jax 0.5.3
- jaxlib 0.5.3
- markdown-it-py 3.0.0
- mdurl 0.1.2
- ml-dtypes 0.5.1
- msgpack 1.1.0
- nest-asyncio 1.6.0
- numpy 2.2.4
- opt-einsum 3.4.0
- optax 0.2.4
- orbax-checkpoint 0.11.10
- packaging 24.2
- pastel 0.2.1
- plotly 5.24.1
- poethepoet 0.33.1
- protobuf 6.30.2
- pygments 2.19.1
- pyyaml 6.0.2
- rich 13.9.4
- scipy 1.15.2
- setuptools 78.1.0
- simple-parsing 0.1.7
- simplejson 3.20.1
- six 1.17.0
- tenacity 9.0.0
- tensorflow-probability 0.25.0
- tensorstore 0.1.73
- tomli 2.2.1
- toolz 1.0.0
- tqdm 4.67.1
- treescope 0.1.9
- typing-extensions 4.13.0
- wrapt 1.17.2
- zipp 3.21.0
- dacite ^1.8.1
- distrax ^0.1.5
- flax ^0.10.2
- plotly ^5.24.1
- poethepoet *
- python ^3.10
- simple-parsing ^0.1.6
- tqdm ^4.67.0