Unsupervised Learning of Object Keypoints for Perception and Control
This work addresses the challenge of sample efficiency and exploration in reinforcement learning for robotics or autonomous systems, representing a novel method for a known bottleneck.
The paper tackles the problem of learning object representations for control and reinforcement learning by introducing Transporter, an unsupervised neural network architecture that discovers geometric keypoints from raw video frames, resulting in more accurate long-term object tracking and enabling highly sample-efficient RL and deep exploration without extrinsic rewards.
The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic segmentation as downstream tasks. In this work we aim to learn object representations that are useful for control and reinforcement learning (RL). To this end, we introduce Transporter, a neural network architecture for discovering concise geometric object representations in terms of keypoints or image-space coordinates. Our method learns from raw video frames in a fully unsupervised manner, by transporting learnt image features between video frames using a keypoint bottleneck. The discovered keypoints track objects and object parts across long time-horizons more accurately than recent similar methods. Furthermore, consistent long-term tracking enables two notable results in control domains -- (1) using the keypoint co-ordinates and corresponding image features as inputs enables highly sample-efficient reinforcement learning; (2) learning to explore by controlling keypoint locations drastically reduces the search space, enabling deep exploration (leading to states unreachable through random action exploration) without any extrinsic rewards.