Skip to content

@HumanCompatibleAI Center for Human-Compatible AI

Change the repository type filter

All

    Repositories list

    59 repositories

    • HighJax

      Public
      Highway driving simulation in JAX for Reinforcement Learning research
      reinforcement-learningjaxdriving-simulator
      reinforcement-learningjaxdriving-simulatorxrlexplainable-reinforcement-learning
      Rust
      •
      MIT License
      •0•7•0•0•Updated Mar 27, 2026Mar 27, 2026

    • ranking-challenge

      Public
      Testing ranking algorithms to improve social cohesion
      Python
      •3•32•1•0•Updated Mar 26, 2025Mar 26, 2025

    • overcooked_ai

      Public
      A benchmark environment for fully cooperative human-AI performance.
      machine-learningreinforcement-learningdeep-learning
      machine-learningreinforcement-learningdeep-learningpytorchartificial-intelligence
      Jupyter Notebook
      •
      MIT License
      •209•953•13•2•Updated Mar 22, 2025Mar 22, 2025

    • tensor-trust

      Public
      A prompt injection game to collect data for robust ML research
      gamesecuritydjango
      gamesecuritydjangoctfhtmxlarge-language-modelsllmprompt-engineeringpromptingllms
      Python
      •
      BSD 2-Clause "Simplified" License
      •8•69•32•4•Updated Jan 27, 2025Jan 27, 2025

    • imitation

      Public
      Clean PyTorch implementations of imitation and reward learning algorithms
      imitation-learninggymnasiuminverse-reinforcement-learning
      imitation-learninggymnasiuminverse-reinforcement-learningreward-learning
      Python
      •
      MIT License
      •301•1.7k•76•19•Updated Jan 7, 2025Jan 7, 2025

    • ranking-challenge-perspective

      Public
      Prosocial Ranking Challenge Perspective Ranker
      Jupyter Notebook
      •
      MIT License
      •0•1•0•1•Updated Nov 26, 2024Nov 26, 2024

    • rc-submission-dante

      Public
      PRC: Testing ranking algorithms to improve social cohesion
      JavaScript
      •3•0•0•0•Updated Sep 21, 2024Sep 21, 2024

    • rc-submission-civirank

      Public
      PRC: Civirank submission
      3•0•0•0•Updated Sep 8, 2024Sep 8, 2024

    • leela-interp

      Public
      Code for "Evidence of Learned Look-Ahead in a Chess-Playing Neural Network"
      Jupyter Notebook
      •
      GNU General Public License v3.0
      •11•27•1•0•Updated Jun 4, 2024Jun 4, 2024

    • tensor-trust-data

      Public
      Dataset for the Tensor Trust project
      Jupyter Notebook
      •5•48•1•0•Updated Mar 17, 2024Mar 17, 2024

    • reward-function-interpretability

      Public
      Jupyter Notebook
      •0•1•4•0•Updated Nov 30, 2023Nov 30, 2023

    • evaluating-rewards

      Public
      Library to compare and evaluate reward functions
      Python
      •
      Apache License 2.0
      •8•68•4•2•Updated Oct 23, 2023Oct 23, 2023

    • seals

      Public
      Benchmark environments for reward modelling and imitation learning algorithms.
      Python
      •
      MIT License
      •9•46•6•1•Updated Sep 19, 2023Sep 19, 2023

    • human_aware_rl

      Public
      Code for "On the Utility of Learning about Humans for Human-AI Coordination"
      Python
      •46•111•0•0•Updated Apr 17, 2023Apr 17, 2023

    • ray

      Public
      A fast and simple framework for building and running distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, …
      Python
      •
      Apache License 2.0
      •7.4k•0•0•9•Updated Mar 4, 2023Mar 4, 2023

    • eirli

      Public
      An Empirical Investigation of Representation Learning for Imitation (EIRLI), NeurIPS'21
      machine-learningpytorchrepresentation-learning
      machine-learningpytorchrepresentation-learningimitation-learningself-supervised-learning
      Python
      •4•37•2•3•Updated Mar 4, 2023Mar 4, 2023

    • nn-clustering-pytorch

      Public
      Checking the divisibility of neural networks, and investigating the nature of the pieces networks can be divided into.
      Python
      •2•6•0•2•Updated Feb 11, 2023Feb 11, 2023

    • overcooked-demo

      Public
      Web application where humans can play Overcooked with AI agents.
      JavaScript
      •28•60•8•6•Updated Dec 6, 2022Dec 6, 2022

    • rl-baselines3-zoo

      Public
      A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
      Python
      •
      MIT License
      •591•1•0•0•Updated Nov 30, 2022Nov 30, 2022

    • sgf-viewer

      Public
      A simple webpage that can visualize a sgf string encoded as a url fragment.
      CSS
      •0•0•0•0•Updated Sep 29, 2022Sep 29, 2022

    • reducing-exploitability

      Public
      Python
      •
      MIT License
      •1•3•0•0•Updated Aug 11, 2022Aug 11, 2022

    • sacred

      Public
      Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
      Python
      •
      MIT License
      •391•1•0•3•Updated Jul 24, 2022Jul 24, 2022

    • assistance-games

      Public
      Supporting code for Assistance Games as a Framework paper
      Python
      •
      MIT License
      •1•3•0•0•Updated Jul 11, 2022Jul 11, 2022

    • dmc2gym

      Public
      OpenAI Gym wrapper for the DeepMind Control Suite
      Python
      •
      MIT License
      •68•2•0•0•Updated Jun 16, 2022Jun 16, 2022

    • katago-driver-bug-repro

      Public
      Docker files to help reproduce bug described in https://forums.developer.nvidia.com/t/kernel-oops-null-pointer-dereference-when-closing-cuda-application-katago/…
      Dockerfile
      •0•0•0•0•Updated May 25, 2022May 25, 2022

    • reward-preprocessing

      Public
      Preprocessing reward functions to make them more interpretable
      Python
      •0•4•0•0•Updated May 11, 2022May 11, 2022

    • multiagent-competition

      Public
      Code for the paper "Emergent Complexity via Multi-agent Competition"
      Python
      •157•4•0•0•Updated Apr 19, 2022Apr 19, 2022

    • adversarial-policies

      Public
      Find best-response to a fixed policy in multi-agent RL
      Python
      •
      MIT License
      •48•288•8•0•Updated Apr 1, 2022Apr 1, 2022

    • stable-baselines3

      Public
      PyTorch version of Stable Baselines, improved implementations of reinforcement learning algorithms.
      Python
      •
      MIT License
      •2.1k•3•0•0•Updated Nov 6, 2021Nov 6, 2021

    • recon-email

      Public
      Script for automatically creating the reconnaissance email.
      HTML
      •1•5•0•0•Updated Nov 2, 2021Nov 2, 2021
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.