Learn How to Cook a New Recipe in a New House: Using Map Familiarization, Curriculum Learning, and Bandit Feedback to Learn Families of Text-Based Adventure Games

TL;DR

This paper introduces a method for training AI agents to learn families of text-based adventure games by combining curriculum learning, environment familiarization, and bandit-based exploration, leading to improved performance on unseen games.

Contribution

It presents a novel approach integrating curriculum learning, environment familiarization, and bandit feedback to enhance AI learning in text-based games, inspired by human learning strategies.

Findings

Agents outperform baselines on unseen games

Curriculum learning accelerates mastery of complex scenarios

Bandit exploration improves environment coverage

Abstract

We consider the task of learning to play families of text-based computer adventure games, i.e., fully textual environments with a common theme (e.g. cooking) and goal (e.g. prepare a meal from a recipe) but with different specifics; new instances of such games are relatively straightforward for humans to master after a brief exposure to the genre but have been curiously difficult for computer agents to learn. We find that the deep Q-learning strategies that have been successfully leveraged for superhuman performance in single-instance action video games can be applied to learn families of text video games when adopting simple strategies that correlate with human-like learning behavior. Specifically, we build agents that learn to tackle simple scenarios before more complex ones using curriculum learning, that familiarize themselves in an unfamiliar environment by navigating before acting, and that explore uncertain environments more thoroughly using contextual multi-armed bandit decision policies. We demonstrate improved task completion rates over reasonable baselines when evaluating on never-before-seen games of that theme.