A nonlinear hidden layer enables actor-critic agents to learn multiple paired association navigation
This addresses a specific challenge in computational neuroscience for researchers studying rodent-like navigation learning, though it appears incremental as it builds on existing agent frameworks.
The study tackled the problem of enabling biologically plausible actor-critic agents to learn multiple paired association navigation tasks, which they previously could not do, by introducing a nonlinear hidden layer that processes place cell and cue information, resulting in successful learning and faster performance with a recurrent reservoir network.
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.