שמור ב:
מידע ביבליוגרפי
Main Authors: Zheng, Chongyi, Tuyls, Jens, Peng, Joanne, Eysenbach, Benjamin
פורמט: Preprint
יצא לאור: 2024
נושאים:
גישה מקוונת:https://arxiv.org/abs/2412.08021
תגים: הוספת תג
אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!
_version_ 1866918158384758784
author Zheng, Chongyi
Tuyls, Jens
Peng, Joanne
Eysenbach, Benjamin
author_facet Zheng, Chongyi
Tuyls, Jens
Peng, Joanne
Eysenbach, Benjamin
contents Self-supervised learning has the potential of lifting several of the key challenges in reinforcement learning today, such as exploration, representation learning, and reward design. Recent work (METRA) has effectively argued that moving away from mutual information and instead optimizing a certain Wasserstein distance is important for good performance. In this paper, we argue that the benefits seen in that paper can largely be explained within the existing framework of mutual information skill learning (MISL). Our analysis suggests a new MISL method (contrastive successor features) that retains the excellent performance of METRA with fewer moving parts, and highlights connections between skill learning, contrastive representation learning, and successor features. Finally, through careful ablation studies, we provide further insight into some of the key ingredients for both our method and METRA.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08021
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning
Zheng, Chongyi
Tuyls, Jens
Peng, Joanne
Eysenbach, Benjamin
Machine Learning
Artificial Intelligence
Self-supervised learning has the potential of lifting several of the key challenges in reinforcement learning today, such as exploration, representation learning, and reward design. Recent work (METRA) has effectively argued that moving away from mutual information and instead optimizing a certain Wasserstein distance is important for good performance. In this paper, we argue that the benefits seen in that paper can largely be explained within the existing framework of mutual information skill learning (MISL). Our analysis suggests a new MISL method (contrastive successor features) that retains the excellent performance of METRA with fewer moving parts, and highlights connections between skill learning, contrastive representation learning, and successor features. Finally, through careful ablation studies, we provide further insight into some of the key ingredients for both our method and METRA.
title Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2412.08021