cassidylaidlaw

boltzmann-policy-distribution

Code and pretrained models for the ICLR 2022 paper "The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models"

cleverhans

An adversarial example library for constructing attacks, building defenses, and benchmarking both

cs285-homework

Assignments for Berkeley CS 285: Deep Reinforcement Learning (Fall 2020)

effective-horizon

Code and data for the paper "Bridging RL Theory and Practice with the Effective Horizon"

fast-pytorch-adversarial-training

hidden-context

Code and data for the paper "Understanding Hidden Context in Preference Learning: Consequences for RLHF"

orpo

perceptual-advex

Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".

python-boilerplate

ReColorAdv

ReColorAdv and other attacks from the NeurIPS 2019 paper "Functional Adversarial Attacks"

cassidylaidlaw/perceptual-advex

Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".

cassidylaidlaw/effective-horizon

Code and data for the paper "Bridging RL Theory and Practice with the Effective Horizon"

cassidylaidlaw/ReColorAdv

ReColorAdv and other attacks from the NeurIPS 2019 paper "Functional Adversarial Attacks"

cassidylaidlaw/cs285-homework

Assignments for Berkeley CS 285: Deep Reinforcement Learning (Fall 2020)

cassidylaidlaw/hidden-context

Code and data for the paper "Understanding Hidden Context in Preference Learning: Consequences for RLHF"

cassidylaidlaw/boltzmann-policy-distribution

Code and pretrained models for the ICLR 2022 paper "The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models"

cassidylaidlaw/python-boilerplate

cassidylaidlaw/fast-pytorch-adversarial-training

cassidylaidlaw/orpo

cassidylaidlaw/cleverhans

An adversarial example library for constructing attacks, building defenses, and benchmarking both

cassidylaidlaw/playing-it-safe

Code for the paper "Playing it Safe: Adversarial Robustness with an Abstain Option"

cassidylaidlaw/malmo

Project Malmo is a platform for Artificial Intelligence experimentation and research built on top of Minecraft. We aim to inspire a new generation of research into challenging new problems presented by this unique environment. --- For installation instructions, scroll down to *Getting Started* below, or visit the project page for more information:

cassidylaidlaw/advex-uar

Code for "Testing Robustness Against Unforeseen Adversaries"

cassidylaidlaw/auto-attack

Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"

cassidylaidlaw/brainwave-sculpture

cassidylaidlaw/django-puppeteer-pdf

Django Wrapper to the Chrome puppeteer to pdf

cassidylaidlaw/django-push-notifications

Send push notifications to mobile devices through GCM or APNS in Django.

cassidylaidlaw/eslint-plugin-sentence-case

ESLint plugin to enforce sentence case in string literals

cassidylaidlaw/Fixup

A Re-implementation of Fixed-update Initialization

cassidylaidlaw/human_aware_rl

Code for "On the Utility of Learning about Humans for Human-AI Coordination"

cassidylaidlaw/iframe-sync

Seamlessly embed dynamic web applications within a static website

cassidylaidlaw/kitsu

🦊 A simple, lightweight & framework agnostic JSON:API client

cassidylaidlaw/llm_optimization

A repo for RLHF training and BoN over LLMs, with support for reward model ensembles.

cassidylaidlaw/microsoftgraph-python

Microsoft Graph API wrapper written in Python

cassidylaidlaw/overcooked-demo

Web application where humans can play Overcooked with AI agents.

cassidylaidlaw/overcooked_ai

A benchmark environment for fully cooperative human-AI performance.

cassidylaidlaw/PyAPNs2

Python library for interacting with the Apple Push Notification service (APNs) via HTTP/2 protocol

cassidylaidlaw/ray

An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.

cassidylaidlaw/resume

My resume, rendered by React

cassidylaidlaw/universe

Universe: a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.