awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
Back to aiframeresearch/spo

Open-source alternatives to AIFrameResearch SPO

30 open-source projects similar to aiframeresearch/spo, ranked by how many features they have in common. Compare stars, activity and what each one does to find the best AIFrameResearch SPO alternative.

  • morvanzhou/pytorch-tutorialMorvanZhou avatar

    MorvanZhou/PyTorch-Tutorial

    8,458View on GitHub↗

    This project is a collection of PyTorch learning resources and educational guides designed to teach the construction and training of neural networks. It serves as a comprehensive deep learning tutorial covering various model architectures and practical implementation strategies. The resources provide specific guidance on implementing computer vision tasks, such as image classification and synthetic imagery generation, as well as reinforcement learning agents using value networks and experience replay. It also covers sequential data modeling through recurrent networks and generative modeling u

    Jupyter Notebookautoencoderbatchbatch-normalization
    View on GitHub↗8,458
  • rlinf/rlinfRLinf avatar

    RLinf/RLinf

    2,502View on GitHub↗

    RLinf is a distributed reinforcement learning orchestrator and embodied AI training framework. It provides the infrastructure to train vision-language-action models and robotic policies using a combination of reinforcement learning and supervised fine-tuning. The system is designed for scaling workloads across GPU clusters, managing the placement of actors, rollout workers, and environment components. It features a specialized robotics data collection pipeline for gathering teleoperated demonstrations and simulation trajectories into standardized replay buffers, alongside a hardware interface

    Pythonagentic-aiembodied-aireinforcement-learning
    View on GitHub↗2,502
  • chanliang/bridgeChanLiang avatar

    ChanLiang/BRIDGE

    6View on GitHub↗

    The code for BRIDGE (Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning).

    View on GitHub↗6

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Find more with AI search
  • chenluye99/profChenluye99 avatar

    Chenluye99/PROF

    11View on GitHub↗

    Introduction

    View on GitHub↗11
  • cjreinforce/pureCJReinforce avatar

    CJReinforce/PURE

    169View on GitHub↗

    2025/10/23 🔥🔥Our paper is accepted by NeurIPS 2025.🔥🔥 - 2025/04/22 Released our Paper on arXiv. See here - 2025/03/24 We re-implement our algorithm based on verl. ✨✨ Key features: (1) add ~50 additional metrics to comprehensively monitor the training process and stability, (2) add a…

    Python
    View on GitHub↗169
  • cmu-aire/mrtCMU-AIRe avatar

    CMU-AIRe/MRT

    119View on GitHub↗

    This repository contains the code for our paper titled "Optimizing Test-Time Compute via Meta Reinforcement Finetuning." In this work, we introduce a novel approach to optimizing test-time compute through meta reinforcement learning, aiming to balance the efficiency and discovery capabilities of…

    Python
    View on GitHub↗119
  • dongguanting/tool-stardongguanting avatar

    dongguanting/Tool-Star

    398View on GitHub↗

    🔧✨Tool-Star: Empowering Multi-Tool Collaborative Web Agent via Reinforcement Learning

    Python
    View on GitHub↗398
  • elliottyan/luffyElliottYan avatar

    ElliottYan/LUFFY

    455View on GitHub↗

    LUFFY: Learning to Reason Under Off‑Policy Guidance A general framework for off-policy learning in large reasoning models.

    Python
    View on GitHub↗455
  • gen-verse/reasonfluxGen-Verse avatar

    Gen-Verse/ReasonFlux

    538View on GitHub↗

    Princeton University \& PKU \& UIUC \& University of Chicago \& ByteDance Seed

    Python
    View on GitHub↗538
  • kwai-klear/klearreasonerKwai-Klear avatar

    Kwai-Klear/KlearReasoner

    82View on GitHub↗

    December 5, 2025 🔍 We propose entropy ratio clipping​ (ERC) to impose a global constraint on the output distribution of the policy model. Experiments demonstrate that ERC can significantly improve the stability of off-policy training. 📄 The paper is available on arXiv.

    Python
    View on GitHub↗82
  • langfengq/verl-agentlangfengQ avatar

    langfengQ/verl-agent

    1,548View on GitHub↗
    Pythonagent-frameworkdeepseek-r1gigpo
    View on GitHub↗1,548
  • liumy2010/uftliumy2010 avatar

    liumy2010/UFT

    31View on GitHub↗

    Mingyang Liu, Gabriele Farina, Asuman Ozdaglar

    Python
    View on GitHub↗31
  • mcgill-nlp/vineppoMcGill-NLP avatar

    McGill-NLP/VinePPO

    192View on GitHub↗

    Paper - Abstract - Updates - Quick Start - Installation - Download the datasets - Create Experiment Script - Single GPU Training (Only for Rho models) - Running the experiments - Code Structure - Initial SFT Checkpoints - Acknowledgement - Citation

    Python
    View on GitHub↗192
  • millioniron/openrlhf-millioniron-millioniron avatar

    millioniron/OpenRLHF-Millioniron-

    2View on GitHub↗

    Open-source / Comprehensive / Lightweight / Easy-to-use

    View on GitHub↗2
  • mozerwang/ampoMozerWang avatar

    MozerWang/AMPO

    51View on GitHub↗

    Minzheng Wang 1,2 , Yongbin Li 3 , Haobo Wang 4 , Xinghua Zhang 3🌟 , Nan Xu 1 , Bingli Wu 3 , Fei Huang 3 , Haiyang Yu 3 , Wenji Mao 1,2🌟

    Python
    View on GitHub↗51
  • multimodal-art-projection/treepomultimodal-art-projection avatar

    multimodal-art-projection/TreePO

    65View on GitHub↗

    This is the official implementation of TreePO algorithm.

    Python
    View on GitHub↗65
  • openai/prm800kopenai avatar

    openai/prm800k

    2,145View on GitHub↗

    This repository accompanies the paper Let's Verify Step by Step and presents the PRM800K dataset introduced there. PRM800K is a process supervision dataset containing 800,000 step-level correctness labels for model-generated solutions to problems from the MATH dataset. More information on…

    Python
    View on GitHub↗2,145
  • prime-rl/implicitprmPRIME-RL avatar

    PRIME-RL/ImplicitPRM

    171View on GitHub↗

    Free Process Rewards without Process Labels

    Python
    View on GitHub↗171
  • prime-rl/primePRIME-RL avatar

    PRIME-RL/PRIME

    1,863View on GitHub↗

    ✨ Getting Started • 📖 Introduction 🔧 Usage • 📃 Evaluation • 🎈 Citation • 🌻 Acknowledgement • 📈 Star History

    Python
    View on GitHub↗1,863
  • ruc-nlpir/arpoRUC-NLPIR avatar

    RUC-NLPIR/ARPO

    1,049View on GitHub↗

    ICLR 2026 Agentic Reinforced Policy Optimization (ARPO)

    Python
    View on GitHub↗1,049
  • ryanliu112/attnrlRyanLiu112 avatar

    RyanLiu112/AttnRL

    14View on GitHub↗

    👋 Hi, everyone! verl is a RL training library initiated by ByteDance Seed team and maintained by the verl community.

    Python
    View on GitHub↗14
  • theroadqaq/reliftTheRoadQaQ avatar

    TheRoadQaQ/ReLIFT

    84View on GitHub↗

    Learning What Reinforcement Learning Can't

    Python
    View on GitHub↗84
  • thudm/treerlTHUDM avatar

    THUDM/TreeRL

    96View on GitHub↗

    Implementation for ACL'25 paper TreeRL: LLM Reinforcement Learning with On-Policy Tree Search. The implementation is based on OpenRLHF

    Python
    View on GitHub↗96
  • tsinghuac3i/intuitive-fine-tuningTsinghuaC3I avatar

    TsinghuaC3I/Intuitive-Fine-Tuning

    30View on GitHub↗

    This repository contains the code for the paper "Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process".

    Python
    View on GitHub↗30
  • wanghanlinhenry/spa-rl-agentWangHanLinHenry avatar

    WangHanLinHenry/SPA-RL-Agent

    86View on GitHub↗
    Python
    View on GitHub↗86
  • yangzhch6/treerpoyangzhch6 avatar

    yangzhch6/TreeRPO

    6View on GitHub↗

    ```bash conda create -n rllm python=3.10 -y conda activate rllm

    Jupyter Notebook
    View on GitHub↗6
  • yaof20/verlyaof20 avatar

    yaof20/verl

    21View on GitHub↗

    👋 Hi, everyone! verl is a RL training library initiated by ByteDance Seed team and maintained by the verl community.

    Python
    View on GitHub↗21
  • yongliang-wu/dftyongliang-wu avatar

    yongliang-wu/DFT

    581View on GitHub↗

    Yizhou Zhou*   Zhou Ziheng   Yingzhe Peng   Xinyu Ye   Xinting Hu   Wenbo Zhu   Lu Qi   Ming-Hsuan Yang   Xu Yang  

    Python
    View on GitHub↗581
  • amap-ml/tree-grpoAMAP-ML avatar

    AMAP-ML/Tree-GRPO

    378View on GitHub↗

    Tree Search for LLM Agent Reinforcement Learning

    Python
    View on GitHub↗378
  • zillwang/stepsearchZillwang avatar

    Zillwang/StepSearch

    72View on GitHub↗

    StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization

    Python
    View on GitHub↗72