Evolving reactive agents with SignalGP
Alexander Lalejini, Charles Ofria · 2018
We introduce SignalGP, a technique for creating digital organisms that harnesses the event-driven programming paradigm. These organisms can evolve to automatically react to signals from the environment or from other agents in a biologically-inspired manner. In addition to introducing SignalGP, we summarize previous results demonstrating the value of the event-driven paradigm in environments dominated by agent-agent and agent-environment interaction. Our full introduction to SignalGP will be published in the proceedings of the 2018 Genetic and Evolutionary Computation Conference (pre-print: https://arxiv.org/pdf/1804.05445.pdf ).