Keywords: deep reinforcement learning, bio-inspired AI, recurrent Q-learning
TL;DR: We report a bio-inspired approach for training a neural network through reinforcement learning to induce high level functions within the network.
Abstract: We report a bio-inspired approach for training a neural network through reinforcement learning to induce high level functions within the network. Based on the interpretation that animals have gained their cognitive functions such as object recognition — without ever being specifically trained for — as a result of maximizing their fitness to the environment, we place our agent in a custom environment where developing certain functions may facilitate decision making; the custom environment is designed as a partially observable Markov decision process in which an input image and the initial value of hidden variables are given to the agent at each time step. We show that our agent, which consists of a convolutional neural network, a recurrent neural network, and a multilayer perceptron, learns to classify the input image and to predict the hidden variables. The experimental results show that high level functions, such as image classification and hidden variable estimation, can be naturally and simultaneously induced without any pre-training or specifying them.