Learning to Learn in Simulation
This addresses the challenge of manual data annotation for robotic platforms, specifically drones, but is incremental as it builds on existing curiosity and reinforcement learning techniques.
The paper tackles the problem of automating training data collection for object detection on a drone by training a curiosity agent using deep reinforcement learning in simulation, achieving a method that can prioritize either speed or minimal human input through a tunable reward function.
Deep learning often requires the manual collection and annotation of a training set. On robotic platforms, can we partially automate this task by training the robot to be curious, i.e., to seek out beneficial training information in the environment? In this work, we address the problem of curiosity as it relates to online, real-time, human-in-the-loop training of an object detection algorithm onboard a drone, where motion is constrained to two dimensions. We use a 3D simulation environment and deep reinforcement learning to train a curiosity agent to, in turn, train the object detection model. This agent could have one of two conflicting objectives: train as quickly as possible, or train with minimal human input. We outline a reward function that allows the curiosity agent to learn either of these objectives, while taking into account some of the physical characteristics of the drone platform on which it is meant to run. In addition, We show that we can weigh the importance of achieving these objectives by adjusting a parameter in the reward function.