Neuro-Nav: A Library for Neurally-Plausible Reinforcement Learning

TL;DR

Neuro-Nav is an open-source library that provides standardized environments and algorithms for neurally plausible reinforcement learning, facilitating research in decision making, navigation, and neural modeling across cognitive science and AI.

Contribution

It introduces a comprehensive, reproducible toolkit for neurally plausible RL, bridging cognitive science and AI research with extendable environments and algorithms.

Findings

Successfully replicates key findings from neural and behavioral studies

Provides a flexible platform for testing new RL algorithms

Enhances reproducibility and transparency in neurally plausible RL research

Abstract

In this work we propose Neuro-Nav, an open-source library for neurally plausible reinforcement learning (RL). RL is among the most common modeling frameworks for studying decision making, learning, and navigation in biological organisms. In utilizing RL, cognitive scientists often handcraft environments and agents to meet the needs of their particular studies. On the other hand, artificial intelligence researchers often struggle to find benchmarks for neurally and biologically plausible representation and behavior (e.g., in decision making or navigation). In order to streamline this process across both fields with transparency and reproducibility, Neuro-Nav offers a set of standardized environments and RL algorithms drawn from canonical behavioral and neural studies in rodents and humans. We demonstrate that the toolkit replicates relevant findings from a number of studies across both cognitive science and RL literatures. We furthermore describe ways in which the library can be extended with novel algorithms (including deep RL) and environments to address future research needs of the field.