GitHub Trends

#python#physics_simulation#reinforcement_learning#robot_learning#robot_manipulation#robotics robosuite v1.5 is a free MuJoCo-powered simulation tool for robot learning, with benchmarks, humanoid robots, custom designs, whole-body controllers, teleop devices, and photo-realistic rendering. It offers modular APIs for easy task creation, sensors, and human demos. You benefit by quickly prototyping robot AI experiments at low cost, ensuring reproducible results without real hardware. https://github.com/ARISE-Initiative/robosuite

#python#agent#llm#llm_agent#llm_reasoning#machine_learning_systems#mlsys#reinforcement_learning#rl AReaL is a free, open-source system for fast asynchronous reinforcement learning to train large AI models in math, coding, search, and agents. It decouples generation and training for up to 2.77x speedup, stable performance, and easy setup on single or 1000+ GPUs with algorithms like GRPO/PPO. Install via git/pip, run examples like GSM8K math instantly. You benefit by building top AI agents affordably and quickly, reproducing results with shared data/models, saving time/money vs. slow synchronous tools. https://github.com/inclusionAI/AReaL

#python#gym#gym_environment#reinforcement_learning#reinforcement_learning_agent#reinforcement_learning_environments#rl_environment#rl_training NeMo Gym helps you build and run reinforcement‑learning training environments for large language models, letting you develop, test, and collect verified rollouts separately from the training loop and integrate with your preferred RL framework and model endpoints (OpenAI, vLLM, etc.). It includes ready resource servers, datasets, and patterns for multi‑step, multi‑turn, and tool‑using scenarios, runs on a typical dev machine (no GPU required), and is early-stage with evolving APIs and docs. Benefit: you can generate high‑quality, verifiable training data faster and plug it into existing training pipelines to improve model behavior. https://github.com/NVIDIA-NeMo/Gym

#python#agent#agentic_ai#llm#mlops#reinforcement_learning Agent Lightning is a tool that helps improve AI agents using reinforcement learning. It allows you to train your agents without making big changes to their code, which is very convenient. You can use it with many different frameworks like LangChain or OpenAI Agent SDK. It also supports various training methods, including reinforcement learning and automatic prompt optimization. This means you can make your agents better at their tasks without a lot of extra work. https://github.com/microsoft/agent-lightning

#mdx#bilateral_teleoperation#force_feedback#genesis#gravity_compensation#humanoid_robot#imitation_learning#machine_learning#moveit2#mujoco#open_source#openarm#python#reinforcement_learning#robot#robot_arm#robotics#ros2#teleoperation OpenArm is a special robot arm that helps with physical AI research. It has 7 degrees of freedom, which means it can move like a human arm. This makes it good for tasks that involve touching or moving things safely around people. The robot is open-source, meaning anyone can build, modify, and use it. This is helpful because it makes advanced robotics available to more people, like researchers and students, without costing too much. A complete system with two arms costs about $6,500, which is much cheaper than similar robots. https://github.com/enactic/openarm

#jupyter_notebook#chatgpt#finance#fingpt#fintech#large_language_models#machine_learning#nlp#prompt_engineering#pytorch#reinforcement_learning#robo_advisor#sentiment_analysis#technical_analysis FinGPT is an open-source AI tool designed specifically for finance, helping you analyze financial news, predict stock prices, and get personalized investment advice quickly and affordably. Unlike costly models like BloombergGPT, FinGPT can be updated frequently with new data at a low cost, making it more accessible and timely. It uses advanced techniques like reinforcement learning from human feedback to tailor advice to your preferences, such as risk tolerance. You can use FinGPT for tasks like sentiment analysis, robo-advising, fraud detection, and portfolio optimization, helping you make smarter financial decisions with up-to-date insights. https://github.com/AI4Finance-Foundation/FinGPT

#python#agent#agentic_ai#grpo#kimi_ai#llms#lora#qwen#qwen3#reinforcement_learning#rl ART is a tool that helps you train smart agents for real-world tasks using reinforcement learning, especially with the GRPO method. The standout feature is RULER, which lets you skip the hard work of designing reward functions by using a large language model to automatically score how well your agent is doing—just describe your task, and RULER takes care of the rest. This makes building and improving agents much faster and easier, works for any task, and often performs as well as or better than hand-crafted rewards. You can install ART with a simple command and start training agents right away, even on your own computer or with cloud resources. https://github.com/OpenPipe/ART