A nonlinear hidden layer enables actor-critic agents to learn multiple paired association navigation

TL;DR

This paper introduces a biologically plausible actor-critic model with a nonlinear hidden layer that successfully learns to navigate to multiple reward locations, overcoming previous limitations of single-location learning.

Contribution

The study demonstrates that adding a nonlinear hidden layer enables biologically plausible agents to learn multiple paired association navigation tasks, a capability previously unachievable.

Findings

Nonlinear hidden layer enables learning multiple reward locations.

Recurrent reservoir network accelerates learning.

Classic agents fail at multi-location navigation without nonlinear processing.

Abstract

Navigation to multiple cued reward locations has been increasingly used to study rodent learning. Though deep reinforcement learning agents have been shown to be able to learn the task, they are not biologically plausible. Biologically plausible classic actor-critic agents have been shown to learn to navigate to single reward locations, but which biologically plausible agents are able to learn multiple cue-reward location tasks has remained unclear. In this computational study, we show versions of classic agents that learn to navigate to a single reward location, and adapt to reward location displacement, but are not able to learn multiple paired association navigation. The limitation is overcome by an agent in which place cell and cue information are first processed by a feedforward nonlinear hidden layer with synapses to the actor and critic subject to temporal difference error-modulated plasticity. Faster learning is obtained when the feedforward layer is replaced by a recurrent reservoir network.