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

Thomas Miconi

Keywords: Evolution, Meta-learning, Neuromodulation, Plasticity

TL;DR: We evolve plastic networks that can automatically acquire novel, cognitive (memory-dependent) tasks (never seen during evolution) from stimuli and rewards alone, much like animals do.

Abstract: 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.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Neuroscience and Cognitive Science (e.g., neural coding, brain-computer interfaces)

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/learning-to-acquire-novel-cognitive-tasks/code)