Tianyu Zhang's repositories
generative-agents
An attempt to build a cheap version of Generative Agents: Interactive Simulacra of Human Behavior
paper-reading-note
和李沐一起读论文
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
ai-economist
Foundation is a flexible, modular, and composable framework to model socio-economic behaviors and dynamics with both agents and governments. This framework can be used in conjunction with reinforcement learning to learn optimal economic policies, as done by the AI Economist (https://www.einstein.ai/the-ai-economist).
arxiv2latex
Download the source latex code of multiple arXiv paper with one click
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
chatGPTBox
Integrating ChatGPT into your browser deeply, everything you need is here
ChatPaper
Use ChatGPT to summarize the arXiv papers.
Chinese-Vicuna
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案,结构参考alpaca
diplomacy_cicero
Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.
ecn
Experiments on Emergent Communication Through Negotiation
emergent-compete
Code for Emergent Communication under Competition (AAMAS 2021)
FAIR
Finite-amplitude Impulse Response simple climate model
Gymnasium
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
hugging-llm
HuggingLLM
ila
Interactive Linear Algebra
language_modeling_via_stochastic_processes
Language modeling via stochastic processes. Oral @ ICLR 2022.
light_mappo
Lightweight version of MAPPO to help you quickly migrate to your local environment.
marl_comm
Basic MARL algorithms with Communication using tianshou and pettingzoo
Multi-Agent-Reinforcement-Learning
PyTorch implements multi-agent reinforcement learning algorithms, including QMIX, Independent PPO, Centralized PPO, Grid Wise Control, Grid Wise Control+PPO, Grid Wise Control+DDPG.
my_ray
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.
open-in-overleaf
Open latex of any arxiv.org paper on overleaf
OpenELM
Evolution Through Large Models
rainbow-is-all-you-need
Rainbow is all you need! A step-by-step tutorial from DQN to Rainbow