Objectworld Experiments
-
Updated
Oct 30, 2017 - MATLAB
Objectworld Experiments
Codepack accompanying "Internal models for interpreting neural population activity during sensorimotor control," by Matthew D. Golub, Byron M. Yu, and Steven M. Chase, eLife 2015.
Inverse optimal control from incomplete trajectory observations, proposing the concept of the recovery matrix which provides further insights into objective learning process.
The project is an implementation of the paper Learning for Control: An Inverse Optimization Approach, co-authored by Syed Adnan Akhtar, Arman Sharifi Kolarijani, and Peyman Mohajerin Esfahani at TU Delft, Netherlands.
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 algorith…
Add a description, image, and links to the inverse-reinforcement-learning topic page so that developers can more easily learn about it.
To associate your repository with the inverse-reinforcement-learning topic, visit your repo's landing page and select "manage topics."