Improbable-AI

Improbable-AI

Geek Repo

Github PK Tool:Github PK Tool

Improbable-AI's repositories

Language:PythonStargazers:2Issues:0Issues:0

walk-these-ways

Sim-to-real RL training and deployment tools for the Unitree Go1 robot.

Language:PythonLicense:NOASSERTIONStargazers:522Issues:0Issues:0

dexenv

Code for Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes (Science Robotics)

Language:PythonLicense:MITStargazers:75Issues:0Issues:0

curiosity_redteam

Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizXgXU)

Language:Jupyter NotebookLicense:MITStargazers:53Issues:0Issues:0

VisionProTeleop

VisionOS App + Python Library to stream head / wrist / finger tracking data from Vision Pro to any robots.

Language:SwiftLicense:MITStargazers:347Issues:0Issues:0

airobot

A python library for robot learning - An extension to PyRobot

Language:PythonLicense:MITStargazers:72Issues:0Issues:0

harness-offline-rl

Official implementation of Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Reweighting

Language:PythonStargazers:15Issues:0Issues:0
Stargazers:0Issues:0Issues:0

dw-offline-rl

Official implementation of NeurIPS'23 paper, Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

Language:PythonStargazers:18Issues:0Issues:0

dribblebot

Code release accompanying DribbleBot: Dynamic Legged Manipulation in the Wild

Language:PythonLicense:NOASSERTIONStargazers:91Issues:0Issues:0

human-guided-exploration

Official codebase for Human Guided Exploration (HuGE)

Language:PythonStargazers:20Issues:0Issues:0

pql

Parallel Q-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation

Language:PythonLicense:MITStargazers:55Issues:0Issues:0

rapid-locomotion-rl

Code for Rapid Locomotion via Reinforcement Learning

Language:PythonLicense:NOASSERTIONStargazers:157Issues:0Issues:0

unitree_legged_sdk

SDK tools for control robots.

Language:C++License:BSD-3-ClauseStargazers:5Issues:0Issues:0

bvn

Official implementation of bilinear value networks

Language:PythonStargazers:1Issues:0Issues:0

eipo

Official codebase for Redeeming Intrinsic Rewards via Constrained Policy Optimization

Language:PythonLicense:MITStargazers:75Issues:0Issues:0

ter

TER codebase for release

Language:PythonStargazers:2Issues:0Issues:0

curiosity_baselines

An open source reinforcement learning codebase with a variety of intrinsic exploration methods implemented in PyTorch.

Language:PythonLicense:MITStargazers:10Issues:0Issues:0

pyrobot

PyRobot: An Open Source Robotics Research Platform

Language:PythonLicense:MITStargazers:2Issues:0Issues:0

agile_flight

Developing and Comparing Vision-based Algorithms for Vision-based Agile Flight

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

ar_track_alvar

AR tag tracking library for ROS

Language:C++Stargazers:0Issues:0Issues:0
Language:PythonLicense:MITStargazers:38Issues:0Issues:0

monkey-job-runner

Monkey Job Runner

Language:PythonStargazers:2Issues:0Issues:0

create_robot

ROS driver for iRobot Create 1 and 2.

Language:C++License:BSD-3-ClauseStargazers:0Issues:0Issues:0

rsl_rl

Fast and simple implementation of RL algorithms, designed to run fully on GPU.

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

legged_gym

Isaac Gym Environments for Legged Robots

Language:PythonLicense:NOASSERTIONStargazers:2Issues:0Issues:0

Azure_Kinect_ROS_Driver

A ROS sensor driver for the Azure Kinect Developer Kit.

Language:C++License:MITStargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0

gym

A toolkit for developing and comparing reinforcement learning algorithms.

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0