Planning from video game descriptions

TL;DR

This paper introduces a method to automatically generate action models from video game descriptions, enabling planning agents to perform and monitor tasks across various games with reduced manual effort.

Contribution

It presents a novel approach for automatic action model generation from game dynamics and integrates it with planning agents, reducing knowledge engineering effort.

Findings

Method effectively generates action models from game descriptions.

Planning agents can solve both deterministic and non-deterministic levels.

Benchmarks created for evaluating planning algorithms in game domains.

Abstract

This project proposes a methodology for the automatic generation of action models from video game dynamics descriptions, as well as its integration with a planning agent for the execution and monitoring of the plans. Planners use these action models to get the deliberative behaviour for an agent in many different video games and, combined with a reactive module, solve deterministic and no-deterministic levels. Experimental results validate the methodology and prove that the effort put by a knowledge engineer can be greatly reduced in the definition of such complex domains. Furthermore, benchmarks of the domains has been produced that can be of interest to the international planning community to evaluate planners in international planning competitions.