Repository History
6 repositories tagged with Reinforcement Learning
ChatArena: Multi-Agent Language Game Environments for LLMs
ChatArena is a Python library designed to provide multi-agent language game environments for Large Language Models (LLMs), aiming to foster the development of communication and collaboration capabilities in AI. It offers a flexible framework for defining players, environments, and interactions based on Markov Decision Processes. Please note that as of August 11, 2025, this project has been deprecated due to a lack of widespread community use and is no longer receiving updates or support.
LLMGym: A Unified Environment for LLM Agent Development and Benchmarking
LLMGym is a unified environment interface designed for developing and benchmarking LLM applications that learn from feedback. It provides a suite of seamlessly swappable environments, making fair and comprehensive comparisons easier for researchers and developers. This project aims to be the "gym" for LLM agents, offering an intuitive interface for various tasks.
Kimi-k1.5: Scaling Reinforcement Learning with LLMs and Multimodality
Kimi-k1.5 introduces an o1-level multi-modal model that significantly advances reinforcement learning with Large Language Models. It demonstrates state-of-the-art performance in short-CoT tasks, outperforming leading models like GPT-4o and Claude Sonnet 3.5, and matches o1 performance in long-CoT scenarios across various modalities. This project highlights key innovations in long context scaling and improved policy optimization.
Verifiers: Environments for LLM Reinforcement Learning and Evaluation
Verifiers is a Python library by Prime Intellect AI for building environments to train and evaluate Large Language Models (LLMs). It enables the creation of custom environments with datasets, model harnesses, and reward functions, supporting reinforcement learning, capability evaluation, and synthetic data generation. This library is tightly integrated with the Prime Intellect ecosystem, including their Environments Hub and training framework.
Open R1: An Open-Source Reproduction of DeepSeek-R1 for Advanced LLM Training
Open R1 is a Hugging Face project dedicated to creating a fully open reproduction of DeepSeek-R1, a powerful reasoning language model. This initiative provides comprehensive tools and recipes for training, evaluating, and generating data for large language models. It fosters community collaboration in AI research, enabling developers to build upon and understand the complex R1 pipeline.
FinRL-Trading: Deep Reinforcement Learning for Automated Stock Trading
FinRL-Trading is a powerful GitHub repository built upon the FinRL framework, designed to develop advanced AI stock-selection and trading strategies. It leverages both Supervised Learning and Deep Reinforcement Learning to create robust models, with capabilities extending to deployment on online trading platforms. This project offers a comprehensive approach to algorithmic trading, from data processing to live paper trading.