Link to originalA related vision for producing general intelligence stems from the open-ended evolution community within the field of artificial life (ALife), which is concerned with developing programs that replicate the emergent complexity characteristic of living systems. Kickstarting a process that exhibits open-endedness—that is, the endless generation of novel complexity—is seen as a key requirement for achieving this goal.
Such an open-ended process may then become an AI generating algorithm (AI-GA), by producing an ecosystem of increasingly complex problems and agents co-evolved to solve them.
However, such a system may constitute a large population of agents specialized to specific challenges. Moreover, exactly how such a co-evolving system might be implemented in practice remains an open question. We propose open-ended learning as a path toward not only an open-ended process, but one resulting in a single, generalist agent capable of dominating (or matching) any other agent in relative general intelligence over time. In this way, open-ended learning bridges the search for open-ended emergent complexity in ALife with the quest for general intelligence in AI.