Git Stars Git Stars

#rl Repositories

Discover 47 active open source GitHub repositories tagged with #rl, accumulating 119,707 total stars (averaging 2,546 stars per project). Leading this topic is LlamaChinese/Llama-Chinese with 14,712 stars.

47
Total Repositories
119,707
Total Stars
2,546
Avg Stars/Repo
1
LlamaChinese/Llama-Chinese

Llama Chinese Community, real-time aggregation of the latest Llama learning materials, building the best Chinese Llama large model open-source ecosystem, fully open-source and commercially available

LlamaChinese
โญ 14,712 Python ๐Ÿ‘ค LlamaChinese Organization ๐Ÿ• Updated 2025-04-06 ๐Ÿ“… Created 2023-07-19
2
thu-ml/tianshou

An elegant PyTorch deep reinforcement learning library.

thu-ml
โญ 11,056 Python ๐Ÿ‘ค thu-ml Organization ๐Ÿ• Updated 2026-04-03 ๐Ÿ“… Created 2018-04-16
3
google/dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

google
โญ 10,934 Jupyter Notebook ๐Ÿ‘ค google Organization ๐Ÿ• Updated 2026-11-12 ๐Ÿ“… Created 2018-07-26
4
OpenPipe/ART

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

OpenPipe
โญ 10,866 Python ๐Ÿ‘ค OpenPipe Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2025-03-10
5
areal-project/AReaL

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

areal-project
โญ 5,926 Python ๐Ÿ‘ค areal-project Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-02-24
6
hiyouga/EasyR1

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

hiyouga
โญ 5,218 Python ๐Ÿ‘ค hiyouga User ๐Ÿ• Updated 2026-11-08 ๐Ÿ“… Created 2025-02-22
7
walkinglabs/hands-on-modern-rl

๐Ÿš€ An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

walkinglabs
โญ 4,936 Jupyter Notebook ๐Ÿ‘ค walkinglabs Organization ๐Ÿ• Updated 2026-10-23 ๐Ÿ“… Created 2026-04-10
8
kubernetes-sigs/agent-sandbox

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).

kubernetes-sigs
โญ 4,673 Go ๐Ÿ‘ค kubernetes-sigs Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-08-12
9
pytorch/rl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

pytorch
โญ 3,640 Python ๐Ÿ‘ค pytorch Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2022-02-01
10
junxiaosong/AlphaZero_Gomoku

An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)

junxiaosong
โญ 3,568 Python ๐Ÿ‘ค junxiaosong User ๐Ÿ• Updated 2024-04-24 ๐Ÿ“… Created 2017-12-21
11
datawhalechina/diy-llm

Covers pre-training data, Tokenizers, Transformers, MoE, distributed training, scaling laws, inference, and alignment. 6 progressive coding assignments for full-stack LLM learning.

datawhalechina
โญ 3,035 Jupyter Notebook ๐Ÿ‘ค datawhalechina Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2025-11-24
12
MaximeVandegar/Papers-in-100-Lines-of-Code

Implementation of papers in 100 lines of code.

MaximeVandegar
โญ 2,915 Python ๐Ÿ‘ค MaximeVandegar User ๐Ÿ• Updated 2026-10-22 ๐Ÿ“… Created 2020-10-26
13
DLR-RM/rl-baselines3-zoo

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

DLR-RM
โญ 2,914 Python ๐Ÿ‘ค DLR-RM Organization ๐Ÿ• Updated 2026-11-14 ๐Ÿ“… Created 2020-05-05
14
werner-duvaud/muzero-general

MuZero implementation

werner-duvaud
โญ 2,877 Python ๐Ÿ‘ค werner-duvaud User ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2019-12-27
15
TsinghuaC3I/Awesome-RL-for-LRMs

A Survey of Reinforcement Learning for Large Reasoning Models

TsinghuaC3I
โญ 2,503 TeX ๐Ÿ‘ค TsinghuaC3I Organization ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2025-03-20
16
FareedKhan-dev/all-rl-algorithms

Implementation of all RL algorithms in a simpler way

FareedKhan-dev
โญ 2,004 Jupyter Notebook ๐Ÿ‘ค FareedKhan-dev User ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2025-03-30
17
PRIME-RL/SimpleVLA-RL

[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

PRIME-RL
โญ 1,916 Python ๐Ÿ‘ค PRIME-RL Organization ๐Ÿ• Updated 2026-01-06 ๐Ÿ“… Created 2025-05-25
18
PRIME-RL/PRIME

Scalable RL solution for advanced reasoning of language models

PRIME-RL
โญ 1,861 Python ๐Ÿ‘ค PRIME-RL Organization ๐Ÿ• Updated 2025-03-18 ๐Ÿ“… Created 2024-12-31
19
zzli2022/Awesome-System2-Reasoning-LLM

Latest Advances on System-2 Reasoning

zzli2022
โญ 1,351 Python ๐Ÿ‘ค zzli2022 User ๐Ÿ• Updated 2025-06-08 ๐Ÿ“… Created 2025-02-09
20
sail-sg/understand-r1-zero

Understanding R1-Zero-Like Training: A Critical Perspective

sail-sg
โญ 1,273 Python ๐Ÿ‘ค sail-sg Organization ๐Ÿ• Updated 2025-08-27 ๐Ÿ“… Created 2025-03-19
21
lasgroup/SDPO

Reinforcement Learning via Self-Distillation (SDPO)

lasgroup
โญ 1,152 Python ๐Ÿ‘ค lasgroup Organization ๐Ÿ• Updated 2026-07-01 ๐Ÿ“… Created 2026-01-24
โญ 1,144 Python ๐Ÿ‘ค RUC-NLPIR Organization ๐Ÿ• Updated 2026-10-11 ๐Ÿ“… Created 2025-07-22
23
PRIME-RL/TTRL

[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning

PRIME-RL
โญ 1,135 Python ๐Ÿ‘ค PRIME-RL Organization ๐Ÿ• Updated 2026-04-15 ๐Ÿ“… Created 2025-04-23
24
JudgmentLabs/judgeval

The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.

JudgmentLabs
โญ 1,073 Python ๐Ÿ‘ค JudgmentLabs Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2024-10-25
25
worldbench/DiffusionOPSD

๐Ÿ”ฅ On-Policy Self-Distillation in Diffusion Models

worldbench
โญ 1,057 Python ๐Ÿ‘ค worldbench Organization ๐Ÿ• Updated 2026-10-12 ๐Ÿ“… Created 2026-07-29
26
tensorlakeai/tensorlake

Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications

tensorlakeai
โญ 1,047 Rust ๐Ÿ‘ค tensorlakeai Organization ๐Ÿ• Updated 2026-11-13 ๐Ÿ“… Created 2024-11-15
27
tingaicompass/AI-Compass

"AI-Compass" will guide the community in navigating the ocean of AI technology. Whether you are a beginner or an advanced developer, you can find a path towards all major AI directions here. It aims to help developers systematically understand AIโ€™s core concepts, mainstream technologies, cuttingโ€‘edge trends, and, through practice, master the entire process from theory to implementation.

tingaicompass
โญ 1,000 Python ๐Ÿ‘ค tingaicompass User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2025-05-27
28
derisk-ai/OpenDerisk

AI-Native Risk Intelligence Systems, OpenDeRiskโ€”โ€”Your application system risk intelligent manager provides 7* 24-hour comprehensive and in-depth protection.

derisk-ai
โญ 986 Python ๐Ÿ‘ค derisk-ai Organization ๐Ÿ• Updated 2026-09-17 ๐Ÿ“… Created 2025-04-23
29
MushroomRL/mushroom-rl

Python library for Reinforcement Learning.

MushroomRL
โญ 946 Python ๐Ÿ‘ค MushroomRL Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2017-02-25
30
chrisliu298/awesome-on-policy-distillation

A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models

chrisliu298
โญ 926 ๐Ÿ‘ค chrisliu298 User ๐Ÿ• Updated 2026-10-06 ๐Ÿ“… Created 2026-03-22
31
Purewhiter/mobilegym

[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research ยท Browser-hosted Android Simulator ยท Verifiable Evaluation ยท Scalable Online RL Training

Purewhiter
โญ 872 Python ๐Ÿ‘ค Purewhiter User ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2026-05-14
32
zeroth-robotics/zeroth-bot

3D-printed open-source humanoid robot platform for sim-to-real and RL

zeroth-robotics
โญ 785 ๐Ÿ‘ค zeroth-robotics Organization ๐Ÿ• Updated 2025-05-24 ๐Ÿ“… Created 2024-09-03
33
Stable-Baselines-Team/stable-baselines3-contrib

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code

Stable-Baselines-Team
โญ 745 Python ๐Ÿ‘ค Stable-Baselines-Team Organization ๐Ÿ• Updated 2026-10-26 ๐Ÿ“… Created 2020-09-20
34
rlresearch/dr-tulu

Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

rlresearch
โญ 729 Python ๐Ÿ‘ค rlresearch Organization ๐Ÿ• Updated 2026-10-09 ๐Ÿ“… Created 2025-11-18
35
benedekrozemberczki/awesome-monte-carlo-tree-search-papers

A curated list of Monte Carlo tree search papers with implementations.

benedekrozemberczki
โญ 717 Python ๐Ÿ‘ค benedekrozemberczki User ๐Ÿ• Updated 2026-01-13 ๐Ÿ“… Created 2019-11-22
36
utilForever/RosettaStone

Hearthstone simulator using C++ with some reinforcement learning

utilForever
โญ 689 C++ ๐Ÿ‘ค utilForever User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2017-05-19
37
facebookresearch/BenchMARL

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.

facebookresearch
โญ 687 Python ๐Ÿ‘ค facebookresearch Organization ๐Ÿ• Updated 2026-02-07 ๐Ÿ“… Created 2023-08-22
38
peteanderson80/Matterport3DSimulator

AI Research Platform for Reinforcement Learning from Real Panoramic Images.

peteanderson80
โญ 664 C++ ๐Ÿ‘ค peteanderson80 User ๐Ÿ• Updated 2024-07-12 ๐Ÿ“… Created 2017-09-29
39
yrlu/irl-imitation

Implementation of Inverse Reinforcement Learning (IRL) algorithms in Python/Tensorflow. Deep MaxEnt, MaxEnt, LPIRL

yrlu
โญ 657 Python ๐Ÿ‘ค yrlu User ๐Ÿ• Updated 2024-05-10 ๐Ÿ“… Created 2017-05-24
40
LightChen233/Awesome-Long-Chain-of-Thought-Reasoning

Latest Advances on Long Chain-of-Thought Reasoning

LightChen233
โญ 644 ๐Ÿ‘ค LightChen233 User ๐Ÿ• Updated 2025-07-18 ๐Ÿ“… Created 2025-03-13
41
neptune-ai/neptune-client

๐Ÿ“˜ The experiment tracker for foundation model training

neptune-ai
โญ 623 Python ๐Ÿ‘ค neptune-ai Organization ๐Ÿ• Updated 2026-03-17 ๐Ÿ“… Created 2019-02-11
42
legubiao/quadruped_ros2_control

ROS2-Control implementations for Quadruped robots, include sim2real

legubiao
โญ 588 C++ ๐Ÿ‘ค legubiao User ๐Ÿ• Updated 2026-02-22 ๐Ÿ“… Created 2024-09-09
43
facebookresearch/meta-agents-research-environments

Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges.

facebookresearch
โญ 581 Python ๐Ÿ‘ค facebookresearch Organization ๐Ÿ• Updated 2026-09-30 ๐Ÿ“… Created 2025-09-11
44
LucasAlegre/morl-baselines

Multi-Objective Reinforcement Learning algorithms implementations.

LucasAlegre
โญ 545 Python ๐Ÿ‘ค LucasAlegre User ๐Ÿ• Updated 2026-09-21 ๐Ÿ“… Created 2022-07-22
45
OpenBMB/DeepThinkVLA

DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models

OpenBMB
โญ 535 Python ๐Ÿ‘ค OpenBMB Organization ๐Ÿ• Updated 2026-09-08 ๐Ÿ“… Created 2025-10-13
46
axon-rl/gem

A Gym for Agentic LLMs

axon-rl
โญ 519 Python ๐Ÿ‘ค axon-rl Organization ๐Ÿ• Updated 2026-01-21 ๐Ÿ“… Created 2025-05-27
47
NVlabs/GDPO

Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

NVlabs
โญ 517 Python ๐Ÿ‘ค NVlabs Organization ๐Ÿ• Updated 2026-05-20 ๐Ÿ“… Created 2025-12-09

Frequently Asked Questions

1

What is the most popular #rl repository on GitHub?

The top ranked open source #rl project on GitHub is LlamaChinese/Llama-Chinese with 14,712 stars. Llama Chinese Community, real-time aggregation of the latest Llama learning materials, building the best Chinese Llama large model open-source ecosystem, fully open-source and commercially available

2

Which programming languages are most used in #rl repositories?

Among the top ranked #rl projects on GitHub, the most common programming languages are Python, Jupyter Notebook, C++, Go.

3

How is the #rl repository ranking calculated?

We track 47 active open source repositories tagged with #rl (500+ stars), totaling 119,707 stars with an average of 2,546 stars per repository. Rankings update daily from the GitHub API.