Constrained novelty search: a study on game content generation

Speeding up Search-Based Algorithms for Level Generation in Physics-Based Puzzle Games

This research uses Machine Learning (ML) techniques in order to aid search-based (SB) algorithms to improve level generation for physics-based puzzle games. These algorithms’ performance are improved by reducing simulation time when the ML techniques are applied. Classification algorithms prevent levels with undesired traits to be evaluated during the simulation phase of the SB procedures. An Angry Birds clone is used for conducting the experiments and results report improvement using the combined approach against every SB algorithm by itself.

Novelty-Driven Cooperative Coevolution

Cooperative coevolutionary algorithms (CCEAs) rely on multiple coevolving populations for the evolution of solutions composed of coadapted components. CCEAs enable, for instance, the evolution of cooperative multiagent systems composed of heterogeneous agents, where each agent is modelled as a component of the solution. Previous works have, however, shown that CCEAs are biased toward stability: the evolutionary process tends to converge prematurely to stable states instead of (near-)optimal solutions. In this study, we show how novelty search can be used to avoid the counterproductive attraction to stable states in coevolution. Novelty search is an evolutionary technique that drives evolution toward behavioural novelty and diversity rather than exclusively pursuing a static objective. We evaluate three novelty-based approaches that rely on, respectively (1) the novelty of the team as a whole, (2) the novelty of the agents' individual behaviour, and (3) the combination of the two. We compare the proposed approaches with traditional fitness-driven cooperative coevolution in three simulated multirobot tasks. Our results show that team-level novelty scoring is the most effective approach, significantly outperforming fitness-driven coevolution at multiple levels. Novelty-driven cooperative coevolution can substantially increase the potential of CCEAs while maintaining a computational complexity that scales well with the number of populations.