Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learning

A hallmark of intelligence is the ability to autonomously learn new flexible, cognitive behaviors - that is, behaviors where the appropriate action depends not just on immediate stimuli (as in simple reflexive stimulus-response associations), but on memorized contextual information. Such cognitive, memory-dependent behaviors are by definition meta-learning tasks. In typical meta-learning experiments, agents are trained with an external, human-designed algorithm to learn a given cognitive task. By contrast, animals are able to pick up new cognitive tasks automatically, from stimuli and rewards alone: evolution has designed animal brains as self-contained reinforcement (meta-)learning systems, capable not just of performing specific cognitive tasks, but of acquiring novel cognitive tasks, including tasks never seen during evolution. Can we harness this process to generate artificial agents with such abilities? Here we evolve neural networks, endowed with plastic connections and neuromodulation, over a sizable set of simple meta-learning tasks based on a framework from computational neuroscience. The resulting evolved networks can automatically modify their own connectivity to acquire a novel simple cognitive task, never seen during evolution, through the spontaneous operation of their evolved neural organization and plasticity system. We suggest that attending to the multiplicity of loops involved in natural learning may provide useful insight into the emergence of intelligent behavior.