https://github.com/vivienneforreal/prma
Prioritized memories activation using Reinforcement Learning
https://github.com/vivienneforreal/prma
dynamic-algorithms dynamic-programming reinforcement-learning successor-representation
Last synced: 2 months ago
JSON representation
Prioritized memories activation using Reinforcement Learning
- Host: GitHub
- URL: https://github.com/vivienneforreal/prma
- Owner: VivienneForReal
- Created: 2024-03-28T15:55:23.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-05-21T18:25:38.000Z (about 1 year ago)
- Last Synced: 2025-03-12T00:28:56.813Z (2 months ago)
- Topics: dynamic-algorithms, dynamic-programming, reinforcement-learning, successor-representation
- Language: Python
- Homepage:
- Size: 4.42 MB
- Stars: 0
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Activation priorisée des souvenirs pour l'apprentissage par renforcement
## Résumé
L'objet du projet est de s'inspirer finement des propriétés d'un modèle de neurosciences computationnelles pour construire un algorithme d'apprentissage par renforcement performant.
## Références
Les articles principaux :
- Prioritized memory access explains planning and hippocampal replay | MG , ND Daw - Nature Neuroscience, 2018 | [Pdf](https://www.biorxiv.org/content/biorxiv/early/2018/05/20/225664.full.pdf)
- Efficient Learning and Planning within the Dyna Framework | Jing Peng, Ronald J. Williams, Adaptive Behavior, 1(4):437-454, 1993 | [pdf](https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=c5fc10768d83ba42a360d861eb96d79fec5d52f4)
- Prioritized experience replay | Schaul, T., Quan, J., Antonoglou, I., & Silver, D. arXiv preprint arXiv:1511.05952, 2015 | [pdf](https://arxiv.org/pdf/1511.05952.pdf)
- [Le dépôt des étudiants de l’an dernier](https://github.com/GabyRkt/Prioritized-Memory-Access)
Diagramme de structure de code :
