Physics games involving tool use for studying human physical representations and rapid trial-and-error learning

PHYRE is a benchmark for physical reasoning.

ROS driver for controlling Boston Dynamics' Spot robot

Wrapper for Boston Dynamics Spot SDK

Code for the paper: "ODIN: A Single Model for 2D and 3D Segmentation" (CVPR 2024)

Python implementation of the NEAT neuroevolution algorithm

ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

[ICRA'23 PT4R] Source code for CLIPGraphs

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

Code for the paper "Eco-evolutionary Dynamics of Non-episodic Neuroevolution in Large Multi-agent Environments"

Utility functions when working with Ai2-THOR. Try to do one thing once.

This repo contains a series of notebook to arrange cultural artifacts and explore patters in metadata. 🎨

Here I recreate the classic game Pocket Tanks, adding a Q-Learning agent to the game!

A repository of links with advice related to grad school applications, research, phd etc