Senior Honors Projects, 2020-current
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Date of Graduation
5-7-2020
Degree Name
Bachelor of Science (BS)
Department
Department of Computer Science
Second Advisor
David H. Bernstein
Third Advisor
Kevin Molloy
Abstract
Text-based games are a very promising space for language-focused machine learning. Within them are huge hurdles in machine learning, like long-term planning and memory, interpretation and generation of natural language, unpredictability, and more. One problem to consider in the realm of natural language interpretation is how to train a machine learning model to understand a text-based game’s objective. This work considers treating this issue like a machine translation problem, where a detailed objective or list of instructions is given as input, and output is a predicted list of actions. This work also explores how a supervised learning system might learn long-term planning and memory through the example of an oracle that always knows the best path. In this exploration, the work here shows that finding this best path is infeasible.
