An ocular biomechanics environment for reinforcement learning

TL;DR

This paper introduces an ocular biomechanics environment for reinforcement learning, demonstrating how an agent can learn to perform rapid eye movements called saccades using deep reinforcement learning techniques.

Contribution

It extends reinforcement learning applications into ocular biomechanics, creating a new environment and demonstrating successful saccade control with a neural network agent.

Findings

Agent achieved mean deviation of 3.5 degrees in saccades

First application of deep RL to ocular biomechanics

Framework advances understanding of eye movement control

Abstract

Reinforcement learning has been applied to human movement through physiologically-based biomechanical models to add insights into the neural control of these movements; it is also useful in the design of prosthetics and robotics. In this paper, we extend the use of reinforcement learning into controlling an ocular biomechanical system to perform saccades, which is one of the fastest eye movement systems. We describe an ocular environment and an agent trained using Deep Deterministic Policy Gradients method to perform saccades. The agent was able to match the desired eye position with a mean deviation angle of 3:5+/-1:25 degrees. The proposed framework is a first step towards using the capabilities of deep reinforcement learning to enhance our understanding of ocular biomechanics.