Open-Ended Reinforcement Learning with Neural Reward FunctionsDownload PDF

Published: 31 Oct 2022, Last Modified: 22 Oct 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: Unsupervised skill discovery, Reinforcement learning
TL;DR: A skill discovery algorithm that learns increasingly complex skills and that works on high-dimensional observation spaces directly, without feature engineering.
Abstract: Inspired by the great success of unsupervised learning in Computer Vision and Natural Language Processing, the Reinforcement Learning community has recently started to focus more on unsupervised discovery of skills. Most current approaches, like DIAYN or DADS, optimize some form of mutual information objective. We propose a different approach that uses reward functions encoded by neural networks. These are trained iteratively to reward more complex behavior. In high-dimensional robotic environments our approach learns a wide range of interesting skills including front-flips for Half-Cheetah and one-legged running for Humanoid. It is the first skill discovery algorithm that can learn such skills without relying on any form of feature engineering. In the pixel-based Montezuma's Revenge environment our method also works with minimal changes and it learns complex skills that involve interacting with items and visiting diverse locations.
Supplementary Material: zip
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](
20 Replies