Examples as Interaction: On Humans Teaching a Computer to Play a Game
Dimitris Kalles, Ilias Fykouras

TL;DR
This paper investigates how humans teach computers to play a game, revealing challenges in combining individual learned models and emphasizing the need for better tools to integrate human input with machine learning.
Contribution
It demonstrates that straightforward composition of human-taught models dilutes learned knowledge, highlighting the complexity of integrating multiple human inputs in machine learning.
Findings
Individual models improve game performance
Straightforward composition dilutes learned knowledge
Need for tools to better combine human teaching and machine learning
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsReinforcement Learning in Robotics · Intelligent Tutoring Systems and Adaptive Learning · Machine Learning and Algorithms
