Distributed Embodied Evolution over Networks
This work addresses adaptive optimization for network agents in dynamic environments, but it appears incremental as it builds on existing Embodied Evolution methods with a focus on distributed interactions.
The paper tackled the problem of optimizing spatially distributed agents in networks where optimal behavior is unknown before deployment, using a distributed Embodied Evolution approach that allows agents to exchange behavior parameters locally. The results showed that local information exchange through crossover improved optimization efficiency compared to cases without such interactions, even with large differences in optimal parameters among neighbors.
In several network problems the optimum behavior of the agents (i.e., the nodes of the network) is not known before deployment. Furthermore, the agents might be required to adapt, i.e. change their behavior based on the environment conditions. In these scenarios, offline optimization is usually costly and inefficient, while online methods might be more suitable. In this work, we use a distributed Embodied Evolution approach to optimize spatially distributed, locally interacting agents by allowing them to exchange their behavior parameters and learn from each other to adapt to a certain task within a given environment. Our results on several test scenarios show that the local exchange of information, performed by means of crossover of behavior parameters with neighbors, allows the network to conduct the optimization process more efficiently than the cases where local interactions are not allowed, even when there are large differences on the optimal behavior parameters within each agent's neighborhood.