Back to Topics Directory
Topic Hub

#reinforcement-learning (30 Repositories)

Ranked open-source repositories tagged with #reinforcement-learning, scored by pull request acceptance likelihood and maintainer engagement velocity.

Topic Avg Merge Rate

72.7%

Avg Review Latency

37.1h

Filter by language

30 repositories tagged #reinforcement-learning

B TierPython 399

upkie/upkie

Open-source wheeled biped robots

100.0%
Merge Rate
<1h
First Review
100%
1st-Timers
1
Maintainers
B TierC++ 190

utilForever/baba-is-auto

Baba Is You simulator using C++ with some reinforcement learning

95.7%
Merge Rate
8h
First Review
100%
1st-Timers
0
Maintainers
S TierPython 887

unilabsim/UniLab

UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms

88.2%
Merge Rate
22h
First Review
77%
1st-Timers
4
Maintainers
B TierMDMDX 2.9k

enactic/openarm

A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.

96.0%
Merge Rate
<1h
First Review
100%
1st-Timers
1
Maintainers
A TierPython 503

hsahovic/poke-env

Poke-env: Python Interface for Pokemon Showdown Bots

94.1%
Merge Rate
17h
First Review
100%
1st-Timers
2
Maintainers
B TierPython 146

bayesianbandits/bayesianbandits

A Pythonic microframework for multi-armed bandit problems

91.8%
Merge Rate
2d
First Review
100%
1st-Timers
0
Maintainers
B TierPython 154

ComputationalPsychiatry/pyhgf

PyHGF: A neural network library for predictive coding

100.0%
Merge Rate
4d
First Review
100%
1st-Timers
0
Maintainers
A TierPython 169

inclusionAI/Awex

A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL workflows

100.0%
Merge Rate
1h
First Review
100%
1st-Timers
2
Maintainers
A TierPython 8.9k

NVlabs/Sana

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

82.9%
Merge Rate
1d
First Review
100%
1st-Timers
2
Maintainers
A TierPython 873 18 GFIs

verl-project/verl-omni

Multimodal RL training framework for diffusion & omni models

73.7%
Merge Rate
2d
First Review
68%
1st-Timers
42
Maintainers
A TierPython 10.7k

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!

73.3%
Merge Rate
1d
First Review
100%
1st-Timers
4
Maintainers
A TierPython 1.1k

hanruihua/ir-sim

A Python-based lightweight robot simulator designed for navigation, control, and learning

81.3%
Merge Rate
17h
First Review
50%
1st-Timers
2
Maintainers
B TierPython 150

RobotControlStack/robot-control-stack

A lean, ROS-free sim-to-real framework for training and deploying Vision-Language-Action (VLA) models and RL agents. Native MuJoCo Gymnasium wrappers with synchronous execution for Franka, UR5e, xArm, SO101 and YAM.

88.9%
Merge Rate
4d
First Review
100%
1st-Timers
0
Maintainers
A TierC++ 6.3k

kvcache-ai/Mooncake

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

70.2%
Merge Rate
20h
First Review
71%
1st-Timers
82
Maintainers
A TierPython 4.7k 101 GFIs

RLinf/RLinf

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

65.8%
Merge Rate
21h
First Review
52%
1st-Timers
76
Maintainers
A TierPython 670

X-GenGroup/Flow-Factory

A unified framework for easy reinforcement learning in Flow-Matching models

73.3%
Merge Rate
1d
First Review
100%
1st-Timers
2
Maintainers
A TierPython 903

Tencent-Hunyuan/UniRL

UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

65.7%
Merge Rate
6h
First Review
56%
1st-Timers
23
Maintainers
B TierPython 57

nissymori/mahjax

A GPU-Accelerated Mahjong Simulator for RL in JAX

91.7%
Merge Rate
2d
First Review
67%
1st-Timers
1
Maintainers
A TierPython 294

hud-evals/hud-python

RL environments + evals for AI agents. Define once, train anything.

69.8%
Merge Rate
1d
First Review
50%
1st-Timers
9
Maintainers
B TierPython 43.7k 14 GFIs

ray-project/ray

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

59.5%
Merge Rate
2d
First Review
51%
1st-Timers
160
Maintainers
B TierPython 5.7k 1 GFIs

areal-project/AReaL

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

42.9%
Merge Rate
14h
First Review
60%
1st-Timers
21
Maintainers
B TierC++ 5.4k

google-deepmind/open_spiel

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

54.5%
Merge Rate
2h
First Review
100%
1st-Timers
14
Maintainers
B TierPython 3.5k

pytorch/rl

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

74.6%
Merge Rate
4d
First Review
86%
1st-Timers
15
Maintainers
B TierPython 1.1k

NVIDIA-NeMo/Gym

Evaluate and improve models and agents using environments

58.0%
Merge Rate
1d
First Review
49%
1st-Timers
66
Maintainers
B TierScala 383

allenai/ScienceWorld

ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.

12.5%
Merge Rate
<1h
First Review
0%
1st-Timers
3
Maintainers
B TierPython 11.2k

wandb/wandb

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

52.8%
Merge Rate
2d
First Review
42%
1st-Timers
25
Maintainers
B TierPython 5.2k 1 GFIs

InternLM/xtuner

A Next-Generation Training Engine Built for Ultra-Large MoE Models

38.9%
Merge Rate
3h
First Review
25%
1st-Timers
12
Maintainers
B TierPython 120 3 GFIs

google/sbsim

100.0%
Merge Rate
8d
First Review
0%
1st-Timers
1
Maintainers
B TierPython 305

inclusionAI/AReno

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

28.6%
Merge Rate
3d
First Review
6%
1st-Timers
73
Maintainers
B TierPython 2.3k

NVlabs/ProtoMotions

ProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.

57.1%
Merge Rate
2d
First Review
100%
1st-Timers
2
Maintainers
Best Reinforcement-learning Open Source Repositories & C-Rank™ | GetMerged