Pinned Repositories
abm-via-irl
azure-api-management-policy-toolkit
Azure API Management policy toolkit is a set of libraries and tools to help managing and testing policies.
cli-tools
Scripting all the things
coba
Contextual bandit benchmarking
coba_prebuilds
Publicly available prebuilt environments for coba.
code-studies
Various projects exploring different language features
emt_experiments
Evaluation of the Eigen Memory Tree on Simulated CB Problems
IRL
A collection of IRL implementations and experiments
kpirl-kla
This repository contains two new algorithms: KPIRL and KLA. KPIRL is a non-linear extension to Abbeel and Ng's Projection IRL algorithm (detailed in "Apprenticeship Learning via Inverse Reinforcement Learning"). KLA is an approximate RL algorithm designed to be used with KPIRL in large state-action spaces without any reward shaping. The algorithms have been published in "Human Apprenticeship Learning via Kernel-based Inverse Reinforcement Learning."
onoff_experiments
Experiments for the online and offline CappedIGW algorithm.
mrucker's Repositories
mrucker/kpirl-kla
This repository contains two new algorithms: KPIRL and KLA. KPIRL is a non-linear extension to Abbeel and Ng's Projection IRL algorithm (detailed in "Apprenticeship Learning via Inverse Reinforcement Learning"). KLA is an approximate RL algorithm designed to be used with KPIRL in large state-action spaces without any reward shaping. The algorithms have been published in "Human Apprenticeship Learning via Kernel-based Inverse Reinforcement Learning."
mrucker/abm-via-irl
mrucker/emt_experiments
Evaluation of the Eigen Memory Tree on Simulated CB Problems
mrucker/onoff_experiments
Experiments for the online and offline CappedIGW algorithm.
mrucker/code-studies
Various projects exploring different language features
mrucker/IRL
A collection of IRL implementations and experiments
mrucker/azure-api-management-policy-toolkit
Azure API Management policy toolkit is a set of libraries and tools to help managing and testing policies.
mrucker/cli-tools
Scripting all the things
mrucker/coba
Contextual bandit benchmarking
mrucker/coba_prebuilds
Publicly available prebuilt environments for coba.
mrucker/data.net
A .NET library written to read, modify, and write large data sets while using minimal processing, memory, and bandwidth
mrucker/dsi-values
An online movie recommendation site for Charlottesville Virginia. The implemented recommendation algorithm is a contextual bandit modification of Abbeel and Ngs "Apprenticeship Learning via Inverse Reinforcement Learning".
mrucker/genieclust
Genie: Fast and Robust Hierarchical Clustering with Noise Point Detection - in Python and R
mrucker/htc_spanish
mrucker/htc_spanish2
mrucker/igw_experiments
Simple IGW Experiments
mrucker/irl-kernel
Convex Optimization Final Project
mrucker/mrucker.github.io
personal website
mrucker/ms-thesis
All code (website, algorithms and plots) for MS Thesis
mrucker/rc-website
The public website for UVA Research Computing
mrucker/uva-archive
An archive of my projects and coursework from UVA
mrucker/vowpal_wabbit
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.