Stanford Intelligent and Interactive Autonomous Systems Group

Stanford Intelligent and Interactive Autonomous Systems Group's repositories

PantheonRL

PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tuning, ad-hoc coordination, and more.

Language:PythonMIT119 7 15

CARLO

2D Driving Simulator

Language:PythonMIT100 7 5

APReL

A Library for Active Preference-based Reward Learning Algorithms

Language:PythonMIT40 5 1

active-preference-based-gpr

Companion code for RSS 2020 paper: "Active Preference-Based Gaussian Process Regression for Reward Learning"

Language:PythonMIT38 5 1

Confidence-Aware-Imitation-Learning

Language:PythonMIT30 6 1

droc

Public release for "Distillation and Retrieving Generalizable Knowledge for Robot Manipulation via Language Corrections"

Language:Python28 5 1

lilac

Companion Codebase for "No, to the Right – Online Language Corrections for Robotic Manipulation via Shared Autonomy"

Language:PythonMIT20 5 1

explore-eqa

Public release for "Explore until Confident: Efficient Exploration for Embodied Question Answering"

Language:Python1600

DPP-Batch-Active-Learning

Companion code to the preprint: E Bıyık, K Wang, N Anari, D Sadigh, "Batch Active Learning using Determinantal Point Processes". arXiv preprint arXiv:1906.07975, Dec. 2019.

Language:Jupyter NotebookMIT13 70

Companion code to TRC paper: Daniel A. Lazar, Erdem Bıyık, Dorsa Sadigh, Ramtin Pedarsani. "Learning how to Dynamically Route Autonomous Vehicles on Shared Roads". Transportation Research Part C: Emerging Technologies, , vol. 130, pp. 103258, 2021; doi: 10.1016/j.trc.2021.103258.

Language:PythonMIT13 30

TREX-pytorch

A PyTorch implementation for the paper 'Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations'.

Language:Python11 50

vla

Code and Experiments for L4DC 2021 Paper: "Learning Visually Guided Latent Actions for Assistive Teleoperation"

Language:PythonGPL-3.011 40

Diverse-Conventions

Exploring techniques to generate diverse conventions in multi-agent settings

Language:JavaScriptGPL-3.09 50

ILEED

Companion code for ICML 2022 paper "Imitation Learning by Estimating Expertise of Demonstrators"

Language:PythonMIT700

multimodal-rewards-from-rankings

Companion code to CoRL 2021 paper "Learning Multimodal Rewards from Rankings"

Language:PythonMIT7 6 1

Learn-Imperfect-Varying-Dynamics

Code for the paper 'Learning from Imperfect Demonstrations from Agents with Varying Dynamics'

Language:PythonMIT600

odyssey

A journey through robotic infrastructure; the ILIAD lab's stack for robotic demonstration collection, policy training, perception, and natural language.

Language:PythonGPL-3.06 6 1