rl repositories
Trending repositories tagged rl, ranked by trending score. Updated daily.
-
1
datawhalechina/diy-llm
Covers pre-training data, Tokenizer, Transformer, MoE,distributed training, Scaling Laws, inference & alignment .6 progressive code assignments for full-stack LLM learning | 涵盖预训练数据、分词器、Transformer、MoE、分布式训练、缩放定律、推理与对齐,6 项渐进代码作业,掌握 LLM 全栈知识
GitHub · Jupyter Notebook · 3,024 stars · 297 forks · +48 stars in 24 hours · Trending score 3.33
-
2
shakewingo/Tadpole
Build an LLM agent from scratch and continuously evolve it.
GitHub · Python · 96 stars · 7 forks · +55 stars in 24 hours · Trending score 3.05
-
3
chrisliu298/awesome-on-policy-distillation
A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models
GitHub · 926 stars · 43 forks · +60 stars in 24 hours · Trending score 2.93
-
4
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).
GitHub · Go · 4,671 stars · 628 forks · +24 stars in 24 hours · Trending score 2.82
-
5
NetX-lab/Libra
Libra: Efficient Resource Management for Agentic RL Post-Training
GitHub · Python · 311 stars · 24 forks · +33 stars in 24 hours · Trending score 2.55
-
6
ASIG-X/JEPLO
First JEPA-based learning framework for mapping-free LiDAR-based perceptive locomotion
GitHub · C++ · 107 stars · 4 forks · +20 stars in 24 hours · Trending score 2.00
-
7
dank/rlapi
Reverse engineered Rocket League internal HTTP & WebSocket API
GitHub · Go · 67 stars · 4 forks · +9 stars in 24 hours · Trending score 1.60
-
8
tingaicompass/AI-Compass
“AI-Compass”将为社区指引在 AI 技术海洋中航行的方向,无论你是初学者还是进阶开发者,都能在这里找到通往 AI 各大方向的路径。旨在帮助开发者系统性地了解 AI 的核心概念、主流技术、前沿趋势,并通过实践掌握从理论到落地的全过程。
GitHub · Python · 1,000 stars · 136 forks · +3 stars in 24 hours · Trending score 1.38
-
9
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
GitHub · Python · 3,639 stars · 539 forks · +1 stars in 24 hours · Trending score 1.31
-
10
AMD-AGI/AMDKernelVault
AMDKernelVault A research and engineering playground for HIP and Triton kernel generation, optimization, and LLM training, including continued pretraining, SFT, and RL (RLHF/RLVR) pipelines.
GitHub · Python · 12 stars · 1 forks · +5 stars in 24 hours · Trending score 1.30
-
11
TsinghuaC3I/Awesome-RL-for-LRMs
A Survey of Reinforcement Learning for Large Reasoning Models
GitHub · TeX · 2,502 stars · 141 forks · 0 stars in 24 hours · Trending score 1.02
-
12
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.
GitHub · Python · 579 stars · 89 forks · 0 stars in 24 hours · Trending score 0.94
-
13
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!
GitHub · Python · 10,856 stars · 1,016 forks · 0 stars in 24 hours · Trending score 0.92
-
14
areal-project/AReaL
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
GitHub · Python · 5,922 stars · 668 forks · 0 stars in 24 hours · Trending score 0.88
-
15
ZJU-REAL/TTPO
TTPO: Test-Time Policy Optimization
GitHub · Python · 74 stars · 6 forks · 0 stars in 24 hours · Trending score 0.68
-
16
tongjingqi/AI-Can-Learn-Scientific-Taste
We propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference modeling and alignment problem.
GitHub · 439 stars · 13 forks · 0 stars in 24 hours · Trending score 0.54
-
17
crusoecloud/crusoe-developer-hub
The Crusoe Developer Hub is the technical home for developers building AI applications and infrastructure on Crusoe Cloud. We publish three kinds of content here: foundational lessons that explain how things work, runnable examples that complete a task end to end, and integrations that connect Crusoe to the tools you already use.
GitHub · Jupyter Notebook · 19 stars · 4 forks · 0 stars in 24 hours · Trending score 0.49
-
18
Purewhiter/mobilegym
[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training
GitHub · Python · 868 stars · 144 forks · 0 stars in 24 hours · Trending score 0.48
-
19
TorchTrade/torchtrade
Modular reinforcement learning framework for algorithmic trading
GitHub · Python · 428 stars · 56 forks · +1 stars in 24 hours · Trending score 0.45
-
20
tensorlakeai/tensorlake
Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications
GitHub · Rust · 1,044 stars · 150 forks · 0 stars in 24 hours · Trending score 0.37
-
21
V01dMur10c/awesome-agent-rl-environments
A curated list of training & evaluation environments for LLM/VLM agents (SWE-Gym, GEM, RAGEN, AgentGym, WebArena, OSWorld, ToolBench…). Updated weekly.
GitHub · 12 stars · 5 forks · 0 stars in 24 hours · Trending score 0.31
-
22
The-Martyr/Awesome-Multimodal-Reasoning
Latest Advances on (RL based) Multimodal Reasoning and Generation in Multimodal LLMs
GitHub · 108 stars · 13 forks · 0 stars in 24 hours · Trending score 0.28
-
23
utilForever/RosettaStone
Hearthstone simulator using C++ with some reinforcement learning
GitHub · C++ · 690 stars · 82 forks · 0 stars in 24 hours · Trending score 0.21
-
24
inclusionAI/AReno
An easy-to-use, fast toolkit to scale up RL post-training on a single node.
GitHub · Python · 389 stars · 141 forks · 0 stars in 24 hours · Trending score 0.21