Learning Not to Learn: Nature versus Nurture in Silico

TL;DR

This paper uses mathematical analysis within a meta-learning framework to explore when it is advantageous for agents to learn adaptive behaviors versus hard-code heuristics, influenced by environmental uncertainty and agent lifetime.

Contribution

It identifies conditions under which meta-learning results in either adaptive learning algorithms or fixed heuristics, highlighting the role of environmental stability and time constraints.

Findings

Meta-learning leads to task-dependent information-integration in certain regimes.

In other regimes, meta-learning results in hard-coded, non-adaptive behaviors.

Non-adaptive behaviors are optimal even when environmental adaptation could be beneficial.

Abstract

Animals are equipped with a rich innate repertoire of sensory, behavioral and motor skills, which allows them to interact with the world immediately after birth. At the same time, many behaviors are highly adaptive and can be tailored to specific environments by means of learning. In this work, we use mathematical analysis and the framework of meta-learning (or 'learning to learn') to answer when it is beneficial to learn such an adaptive strategy and when to hard-code a heuristic behavior. We find that the interplay of ecological uncertainty, task complexity and the agents' lifetime has crucial effects on the meta-learned amortized Bayesian inference performed by an agent. There exist two regimes: One in which meta-learning yields a learning algorithm that implements task-dependent information-integration and a second regime in which meta-learning imprints a heuristic or 'hard-coded' behavior. Further analysis reveals that non-adaptive behaviors are not only optimal for aspects of the environment that are stable across individuals, but also in situations where an adaptation to the environment would in fact be highly beneficial, but could not be done quickly enough to be exploited within the remaining lifetime. Hard-coded behaviors should hence not only be those that always work, but also those that are too complex to be learned within a reasonable time frame.