Stars
AIRA-dojo: a framework for developing and evaluating AI research agents
🌎💪 BrowserGym, a Gym environment for web task automation
Reward Evolution with Large Language Models using Human Feedback
🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL
A generative world for general-purpose robotics & embodied AI learning.
Document to Markdown OCR library with Llama 3.2 vision
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
Python 3.8+ toolbox for submitting jobs to Slurm
DSPy: The framework for programming—not prompting—language models
Symk is a state-of-the-art classical optimal and top-k planner.
A curated list of awesome knowledge-driven autonomous driving (continually updated)
A PDDL library that parse PDDL files and provides a very simple interface to interact with domain-problems.
Poke-env: Python Interface for Pokemon Showdown Bots
Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).
TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.
General library for setting up linux-based environments for developing, running, and evaluating planners.
An extensible benchmark for evaluating large language models on planning
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
Examples of robotic manipulation using DeepMind's MuJoCo framework.
A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites
A comprehensive list of PAPERS, CODEBASES, and, DATASETS on Decision Making using Foundation Models including LLMs and VLMs.
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
[CVPR 2024] The code for paper 'Towards Learning a Generalist Model for Embodied Navigation'
Official code release of AAAI 2024 paper SayCanPay.
Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...