Data

Tools

Indexes

Applications

Experiments

Repos

An open API service providing repository metadata for many open source software ecosystems.

GitHub topics: fedrl

flint-xf-fan/Federated-RLHF

[AAMAS 2025] Privacy-preserving and Personalized RLHF, with convergence guarantees. The Code contains experiments for training multiple instances of GPT-2 for personalized sentiment aligned text generation.

Language: Python - Size: 742 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 6 - Forks: 0

flint-xf-fan/Byzantine-Federated-RL

[NeurIPS2021] Federated Reinforcement Learning with Theoretical Guarantees. The repo contains code and experiments for our Federated Policy Gradient with Byzantine Resilience framework for improving sample efficiency of RL agents.

Language: Python - Size: 446 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 92 - Forks: 12

Related Keywords
federated-reinforcement-learning 2 fedrl 2 federated-rlhf 1 fedrlhf 1 llms 1 personalized-rlhf 1 reinforcement-learning-from-human-feedback 1 rft 1 rlhf 1 byzantine-reinforcement-learning 1 federated-learning 1 policy-gradient 1 reinforcement-learning 1 sample-efficient-rl 1