rddy

ReQueST

Code for the paper, "Learning Human Objectives by Evaluating Hypothetical Behavior"

deepassist

Shared autonomy via deep reinforcement learning

deeptutor

Spaced repetition through deep reinforcement learning

leitnerq

A queueing network model for spaced repetition

isql

Inferring beliefs about dynamics from behavior

mimi

Code for the paper, "First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization"

pico

Code for the paper, "Pragmatic Image Compression for Human-in-the-Loop Decision-Making"

ASE

Code for the paper, "Assisted Perception: Optimizing Observations to Communicate State"

lentil

An implementation of the Latent Skill Embedding model

sqil-atari

Implementation of SQIL for Atari games

asha

bairblog.github.io

ggrl

RL experiments

papers

rddy.github.io

x2t

Code for the paper, "X2T: Training an X-to-Text Typing Interface with Online Learning from User Feedback"