Alternatives and similar repositories for microGRPO

Users that are interested in microGRPO are comparing it to the libraries listed below

• upiterbarg / diff_history
  [ICML 2024] Official code release accompanying the paper "diff History for Neural Language Agents" (Piterbarg, Pinto, Fergus)
  ☆20Updated last year
• McGill-NLP / VinePPO
  Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"
  ☆184Updated 8 months ago
• tyler-romero / microR1
  Simple repository for training small reasoning models
  ☆48Updated 11 months ago
• mnoukhov / async_rlhf
  Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models
  ☆68Updated 9 months ago
• facebookresearch / oni
  Learn online intrinsic rewards from LLM feedback
  ☆45Updated last year
• lucidrains / ppo
  An implementation of PPO in Pytorch
  ☆106Updated 3 weeks ago
• mklissa / maestromotif
  Skill Design From AI Feedback
  ☆33Updated 11 months ago
• entity-neural-network / enn-trainer
  Reinforcement learning training framework for entity-gym environments.
  ☆17Updated last year
• Sea-Snell / Implicit-Language-Q-Learning
  Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"
  ☆210Updated 2 years ago
• CLAIRE-Labo / EvoTune
  Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.
  ☆125Updated 2 months ago
• ttumiel / minRLHF
  Minimal RLHF implementation built on top of minGPT.
  ☆32Updated last year
• open-thought / tiny-grpo
  Minimal hackable GRPO implementation
  ☆319Updated 11 months ago
• lowrollr / turbozero
  fast + parallel AlphaZero in JAX
  ☆109Updated last year
• vwxyzjn / cleanba
  CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL
  ☆122Updated last year
• sethkarten / pokechamp
  Official repository of the spotlight ICML 2025 paper, PokeChamp: an Expert-level Minimax Language Agent.
  ☆134Updated 3 months ago
• codingfisch / flashrl
  Fast reinforcement learning 💨
  ☆28Updated 6 months ago
• Asap7772 / understanding-rlhf
  Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…
  ☆32Updated last year
• keraJLi / synthetic-gymnax
  Drop-in environment replacements that make your RL algorithm train faster.
  ☆21Updated last year
• jrosseruk / Torch2Jax-DeepSeek-R1-Distill-Qwen-1.5B
  Flax (Jax) implementation of DeepSeek-R1-Distill-Qwen-1.5B with weights ported from Hugging Face.
  ☆26Updated 11 months ago
• abdulhaim / LMRL-Gym
  ☆110Updated last year
• TextArena / UnstableBaselines
  ☆116Updated last week
• Edward-Sun / gpt-accelera
  Simple and efficient pytorch-native transformer training and inference (batched)
  ☆79Updated last year
• ServiceNow / PipelineRL
  A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
  ☆357Updated this week
• joey00072 / nanoGRPO
  nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)
  ☆141Updated 8 months ago
• kanishkg / stream-of-search
  Repository for the paper Stream of Search: Learning to Search in Language
  ☆152Updated 11 months ago
• maxencefaldor / omni-epic
  OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (ICLR 2025).
  ☆73Updated last year
• hamishivi / EasyLM
  Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…
  ☆78Updated last year
• hr0nix / omega
  A number of agents (PPO, MuZero) with a Perceiver-based NN architecture that can be trained to achieve goals in nethack/minihack environm…
  ☆43Updated 3 years ago
• clement-bonnet / lpn
  Latent Program Network (from the "Searching Latent Program Spaces" paper)
  ☆107Updated 2 months ago
• Cornell-RL / tril
  ☆128Updated last year