Learning of feature points without additional supervision improves reinforcement learning from images

TL;DR

This paper introduces an end-to-end method for learning feature points directly from images, enhancing reinforcement learning performance without extra supervision or pre-training, and achieving results comparable to state-of-the-art methods.

Contribution

It presents a differentiable feature point extractor integrated into reinforcement learning, eliminating the need for pre-training or auxiliary losses.

Findings

Achieves competitive performance on DeepMind Control Suite tasks.

Eliminates the need for unsupervised pre-training or additional supervision.

Provides an efficient end-to-end learning framework for feature points.

Abstract

In many control problems that include vision, optimal controls can be inferred from the location of the objects in the scene. This information can be represented using feature points, which is a list of spatial locations in learned feature maps of an input image. Previous works show that feature points learned using unsupervised pre-training or human supervision can provide good features for control tasks. In this paper, we show that it is possible to learn efficient feature point representations end-to-end, without the need for unsupervised pre-training, decoders, or additional losses. Our proposed architecture consists of a differentiable feature point extractor that feeds the coordinates of the estimated feature points directly to a soft actor-critic agent. The proposed algorithm yields performance competitive to the state-of-the art on DeepMind Control Suite tasks.