Data to Actionable Knowledge (DtAK) Lab

policy-summarization-with-user-models-public

batch-apprenticeship-learning

Truly Batch Apprenticeship Learning with Deep Successor Features.

tutorial-rl

DIPG-public

Demonstration of Diversity Inducing Policy Gradient (DIPG)

mimic_icu_datapackage

Public resource for curated ICU dataset used in time-series analysis tasks, such as in AMIA CRI 2017 paper by Ghassemi, Wu, Hughes, et al.

Q-Transfer-Demo-public-

A demonstration showing the Q-Transform approach for initializing Non-negative Matrix Factorizations

demo_tex_project_with_overleaf

Shows how to make a git repository for LaTeX document sync'd with Overleaf

MappingGPPstoBNNS

maps a gpp to a bnn

tree-regularization-public

Code for AAAI 2018 accepted paper: "Beyond Sparsity: Tree Regularization of Deep Models for Interpretability"

hip-mdp-public

Code for training and testing a Hidden Parameter Markov Decision Process, used to facilitate the transfer of learning

hs-bnn-public

cs282np-public

repository for CS282R: Bayesian Nonparametrics assignments

cs282rl-public

Domains and other useful code for Harvard CS 282r on Reinforcement Learning