Unsupervisedly Learned Representations: Should the Quest be Over?
This work suggests that pursuing unsupervised learning in simulated environments may be futile, impacting researchers in machine learning and AI seeking to bridge the gap with biological intelligence.
The paper addresses the 20% accuracy gap between unsupervised learned representations and animal intelligence by proposing reinforcement learning as a solution that achieves comparable accuracy, noting it is unsupervised in real-world environments but supervised in simulated ones.
After four decades of research there still exists a Classification accuracy gap of about 20% between our best Unsupervisedly Learned Representations methods and the accuracy rates achieved by intelligent animals. It thus may well be that we are looking in the wrong direction. A possible solution to this puzzle is presented. We demonstrate that Reinforcement Learning can learn representations which achieve the same accuracy as that of animals. Our main modest contribution lies in the observations that: a. when applied to a real world environment Reinforcement Learning does not require labels, and thus may be legitimately considered as Unsupervised Learning, and b. in contrast, when Reinforcement Learning is applied in a simulated environment it does inherently require labels and should thus be generally be considered as Supervised Learning. The corollary of these observations is that further search for Unsupervised Learning competitive paradigms which may be trained in simulated environments may be futile.