Scott (ScottJordan)

ScottJordan

Geek Repo

Twitter:@UMassScott

Github PK Tool:Github PK Tool


Organizations
DecisionMakingAI

Scott's repositories

EvaluationOfRLAlgs

This repository contains the code used in the paper Evaluating the Performance of Reinformcent Learning Algorithms

Language:Jupyter NotebookLicense:MITStargazers:27Issues:2Issues:0

SafePolicyImprovementNonstationary

This a repository containing the code for the paper "Towards Safe Policy Improvement forNon-Stationary MDPs"

Language:Jupyter NotebookStargazers:3Issues:1Issues:0

TangoRobot

Using a Project Tango Tablet mounted on a robot we are applying machine learning techniques to have it complete tasks on a small field

Language:C++License:Apache-2.0Stargazers:2Issues:2Issues:0

ros_rl

A ROS package for setting up reinforcement learning environments and agent for training in both simulation and on actual robots.

Language:PythonLicense:MITStargazers:1Issues:0Issues:0

dcs_bfi_fitting

Code for fitting BFI to measurements

Language:Jupyter NotebookStargazers:0Issues:1Issues:0

ml-agents

Unity Machine Learning Agents Toolkit

Language:C#License:NOASSERTIONStargazers:0Issues:0Issues:0

OnlineStats.jl

Single-pass algorithms for statistics

Language:JuliaLicense:MITStargazers:0Issues:0Issues:0

python-rllib

A library of RL algorithms in python for both linear and nonlinear function approximation.

Language:PythonLicense:MITStargazers:0Issues:0Issues:0
Language:HTMLLicense:MITStargazers:0Issues:1Issues:0

umassthesis

Unofficial UMass thesis style files for use with LaTeX

Language:TeXStargazers:0Issues:0Issues:0
Language:PythonLicense:MITStargazers:0Issues:0Issues:0