Control and Creation: Coevolution of Game Levels and Gameplaying Agents
Open-endedness, primarily studied in the context of artificial life, is the ability of systems to generate potentially unbounded ontologies of increasing novelty and complexity. Engineering generative systems displaying at least some degree of this ability is a goal with clear applications to procedural content generation in games. The Paired Open-Ended Trailblazer (POET) algorithm, heretofore explored only in a biped walking domain, is a coevolutionary system that simultaneously generates environments and agents that can solve them. This paper adapts the POET algorithm for the purpose of co-generating levels for multiple video games and agents that can successfully play them. The resulting system, called PINSKY, leverages the General Video Game Artificial Intelligence (GVGAI) framework to enable cogeneration of levels and agents for the 2D Atari-style games of Zelda and Solar Fox. These games present a more complex challenge than biped locomotion because behaviors of other agents (i.e. enemies) must be accounted for and tasks often have a sequential form where agents must complete tasks in a specific order to be successful. Furthermore, the reward schemes are extremely sparse and potentially distracting. Results demonstrate the ability of PINSKY to generate lineages of increasingly complex (yet winnable) game levels, opening up a promising new avenue for research at the intersection of procedural content generation and artificial life. Furthermore, results look into necessary conditions for POET-style algorithms and illuminate the necessity of transfer learning. At the same time, results in these challenging game domains highlight the limitations of the current algorithm and opportunities for improvement.
Computer science|Artificial intelligence
Dharna, Aaron, "Control and Creation: Coevolution of Game Levels and Gameplaying Agents" (2020). ETD Collection for Fordham University. AAI28002437.