Stars
Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals
Search, understand, reproduce, and improve an idea with ease
RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI
Official Repo for Open-Reasoner-Zero
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
Repo of paper "Free Process Rewards without Process Labels"
Scalable RL solution for advanced reasoning of language models
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
GUI for a Vocal Remover that uses Deep Neural Networks.
Generative Agents: Interactive Simulacra of Human Behavior
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
Web application where humans can play Overcooked with AI agents.
Code for "On the Utility of Learning about Humans for Human-AI Coordination"
A benchmark environment for fully cooperative human-AI performance.
Diversity is All You Need: Learning Skills without a Reward Function in PyTorch.
A minimalist environment for decision-making in autonomous driving
Implementations of IQL, QMIX, VDN, COMA, QTRAN, MAVEN, CommNet, DyMA-CL, and G2ANet on SMAC, the decentralised micromanagement scenario of StarCraft II