General policy mapping: online continual reinforcement learning inspired on the insect brain

Angel Yanguas-Gil, Sandeep Madireddy

Keywords: online reinforcement learning, insect brain, continual reinforcement learning

TL;DR: Architecture inspired on the insect brain excel in online continual reinforcement learning of open world environment tasks

Abstract: We have developed a model for online continual reinforcement learning (RL) inspired on the insect brain. Our model leverages the offline training of a feature extraction and a common general policy layer to enable the convergence of RL algorithms in online settings. Sharing a common policy layer across tasks leads to positive backward transfer, where the agent continuously improved in older tasks sharing the same underlying general policy. Biologically inspired restrictions to the agent's network are key for the convergence of RL algorithms. This provides a pathway towards efficient online RL in resource-constrained scenarios.