A domain-independent problem-solving system based on principles of Artificial Life is introduced. In this system, DIAS, the input and output dimensions of the domain are laid out in a spatial medium. A population of actors, each seeing only part of this medium, solves problems collectively in it. The process is independent of the domain and can be implemented through different kinds of actors. Through a set of experiments on various problem domains, DIAS is shown able to solve problems with different dimensionality and complexity, to require no hyperparameter tuning for new problems, and to exhibit lifelong learning, i.e. adapt rapidly to run-time changes in the problem domain, and do it better than a standard non-collective approach. DIAS therefore demonstrates a role for Alife in building scalable, general, and adaptive problem-solving systems.

In order to deploy autonomous agents to domains such as autonomous driving, infrastructure management, health care, and finance, they must be able to adapt safely to unseen situations. The current approach in constructing such agents is to try to include as much variation into training as possible, and then generalize within the possible variations. This paper proposes a principled approach where a context module is coevolved with a skill module. The context module recognizes the variation and modulates the skill module so that the entire system performs well in unseen situations. The approach is evaluated in a challenging version of the Flappy Bird game where the effects of the actions vary over time. The Context+Skill approach leads to significantly more robust behavior in environments with previously unseen effects. Such a principled generalization ability is essential in deploying autonomous agents in real world tasks, and can serve as a foundation for continual learning as well.

Collaboration in order to perform various tasks such as herding or hunting is frequently seen in nature. Cooperative behaviors benefit the group by helping them achieve rewards that would not be possible for an individual to achieve alone. In addition to cooperative hunting, spotted hyenas also participate in coordinated mobbing of lions, which is a complex behavior that is still believed to be genetic. Lions are larger and stronger than hyenas, and therefore the hyenas need to cooperate in large numbers to overcome their fear and attack the lions. Individualistic hyena traits and other factors that may affect the frequency or success of lion-mobbing have not been studied in simulation before. Furthermore, multiple emotions, such as fear and affiliation towards teammates, affect the willingness of hyenas to attack lions. The computational model of lion-hyena interaction developed in this work can help understand the evolution of mobbing behaviors. It may be used in the future to evolve strategies in video game characters to overcome powerful adversaries or solve problems that involve high risk.

An important benefit of multi-objective search is that it maintains a diverse population of candidates, which helps in deceptive problems in particular. Not all diversity is useful, however: candidates that optimize only one objective while ignoring others are rarely helpful. This paper proposes a solution: The original objectives are replaced by their linear combinations, thus focusing the search on the most useful tradeoffs between objectives. To compensate for the loss of diversity, this transformation is accompanied by a selection mechanism that favors novelty. In the highly deceptive problem of discovering minimal sorting networks, this approach finds better solutions, and finds them faster and more consistently than standard methods. It is therefore a promising approach to solving deceptive problems through multi-objective optimization.

Computational simulation of language evolution provides valuable insights into the origin of language. Simulating the evolution of language among agents in an artificial world also presents an interesting challenge in evolutionary computation and machine learning. In this paper, a jungle world is constructed where agents must accomplish different tasks such as hunting and mating by evolving their own language to coordinate their actions. In addition, all agents must acquire the language during their lifetime through interaction with other agents. This paper proposes the algorithm of Evolutionary Reinforcement Learning with Potentiation and Memory (ERL-POM) as a computational approach for achieving this goal. Experimental results show that ERL-POM is effective in situated simulation of language evolution, demonstrating that languages can be evolved in the artificial environment when communication is necessary for some or all of the tasks the agents perform.

Novelty search is a powerful biologically motivated method for discovering successful behaviors especially in deceptive domains, like those in artificial life. This paper extends the biological motivation further by distributing novelty search to run in parallel in multiple islands, with periodic migration among them. In this manner, it is possible to scale novelty search to larger populations and more diverse runs, and also to harness available computing power better. A second extension is to improve novelty searchs ability to solve practical problems by biasing the migration and elitism towards higher fitness. The resulting method, DANS, is shown to find better solutions much faster than pure single-population novelty search, making it a promising candidate for solving deceptive design problems in the real world.