6 Repos
Awesome GitHub RepositoriesCritic-Based Algorithms
Reinforcement learning approaches that utilize value functions or process verifiers.
Explore 6 awesome GitHub repositories matching part of an awesome list · Critic-Based Algorithms. Refine with filters or upvote what's useful.
Awesome Critic-Based Algorithms GitHub Repositories
Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
- open-reasoner-zero/open-reasoner-zero
Open-Reasoner-Zero/Open-Reasoner-Zero
2,095Auf GitHub ansehenAn Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
Scaling reinforcement learning on base models using open approaches.
Python - prime-rl/prime
PRIME-RL/PRIME
1,863Auf GitHub ansehen✨ Getting Started • 📖 Introduction 🔧 Usage • 📃 Evaluation • 🎈 Citation • 🌻 Acknowledgement • 📈 Star History
Process reinforcement learning using implicit reward signals.
Python - lifan-yuan/implicitprm
lifan-yuan/ImplicitPRM
Free Process Rewards without Process Labels
Generating process rewards without requiring explicit process labels.
Python - rookie-joe/autopsv
rookie-joe/AutoPSV
This repository contains the official implementation of AutoPSV: Automated Process-Supervised Verifier, accepted at NeurIPS 2024 (poster).
Automated verification for process-supervised reinforcement learning.
Python - corl-team/vl-dac
corl-team/VL-DAC
Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success
Reinforcement learning for vision-language models in synthetic environments.
Python - hitsz-tmg/veripo
HITsz-TMG/VerIPO
📄 Paper Link 🤗 VerIPO-7B-v1.0
Iterative policy optimization for long-reasoning video models.
Python
