Examples as Interaction: On Humans Teaching a Computer to Play a Game

by   Dimitris Kalles, et al.

This paper reviews an experiment in human-computer interaction, where interaction takes place when humans attempt to teach a computer to play a strategy board game. We show that while individually learned models can be shown to improve the playing performance of the computer, their straightforward composition results in diluting what was earlier learned. This observation suggests that interaction cannot be easily distributed when one hopes to harness multiple human experts to develop a quality computer player. This is related to similar approaches in robot task learning and to classic approaches to human learning and reinforces the need to develop tools that facilitate the mix of human-based tuition and computer self-learning.




On Measuring the Impact of Human Actions in the Machine Learning of a Board Game's Playing Policies

We investigate systematically the impact of human intervention in the tr...

Player-AI Interaction: What Neural Network Games Reveal About AI as Play

The advent of artificial intelligence (AI) and machine learning (ML) bri...

Playing Go without Game Tree Search Using Convolutional Neural Networks

The game of Go has a long history in East Asian countries, but the field...

Learning Language Games through Interaction

We introduce a new language learning setting relevant to building adapti...

Towards a Sociolinguistics-Based Framework for the Study of Politeness in Human-Computer Interaction

Politeness plays an important role in regulating communication and enhan...

Unraveling Go gaming nature by Ising Hamiltonian and common fate graphs: tactics and statistics

Go gaming is a struggle between adversaries, black and white simple ston...

Three Patterns to Support Empathy in Computer-Mediated Human Interaction

We present three patterns for computer-mediated interaction which we dis...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.