This repository includes the code used to perform the examples and simulations in our paper: "Learning the Human's Interaction Strategy" (in process). We also have included the results from our simulation, which were used to generate the result figures in our paper.
This folder contains the code used to generate the example in Section IV-C, where the robot is learning to sort screws from a human expert.
This folder contains the code used to generate the example in Section V-D, where the robot is teaching the human which goal it is attempting to reach.
This folder contains the code used to perform the "Learning Simulations" in Section VI. The human provides a policy demonstration, and the robot is attempting to learn the human's reward parameters.