Salvato in:
Dettagli Bibliografici
Autori principali: Xiao, Ting, Zheng, Jiakun, Yang, Rushuai, Xu, Kang, Zhang, Qiaosheng, Liu, Peng, Bai, Chenjia
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.14420
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918061602242560
author Xiao, Ting
Zheng, Jiakun
Yang, Rushuai
Xu, Kang
Zhang, Qiaosheng
Liu, Peng
Bai, Chenjia
author_facet Xiao, Ting
Zheng, Jiakun
Yang, Rushuai
Xu, Kang
Zhang, Qiaosheng
Liu, Peng
Bai, Chenjia
contents Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill learning. However, entropy-based exploration struggles in large-scale state spaces (e.g., images), and empowerment-based methods with Mutual Information (MI) estimations have limitations in state exploration. To address these challenges, we propose a novel skill discovery objective that maximizes the deviation of the state density of one skill from the explored regions of other skills, encouraging inter-skill state diversity similar to the initial MI objective. For state-density estimation, we construct a novel conditional autoencoder with soft modularization for different skill policies in high-dimensional space. Meanwhile, to incentivize intra-skill exploration, we formulate an intrinsic reward based on the learned autoencoder that resembles count-based exploration in a compact latent space. Through extensive experiments in challenging state and image-based tasks, we find our method learns meaningful skills and achieves superior performance in various downstream tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14420
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unsupervised Skill Discovery through Skill Regions Differentiation
Xiao, Ting
Zheng, Jiakun
Yang, Rushuai
Xu, Kang
Zhang, Qiaosheng
Liu, Peng
Bai, Chenjia
Machine Learning
Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill learning. However, entropy-based exploration struggles in large-scale state spaces (e.g., images), and empowerment-based methods with Mutual Information (MI) estimations have limitations in state exploration. To address these challenges, we propose a novel skill discovery objective that maximizes the deviation of the state density of one skill from the explored regions of other skills, encouraging inter-skill state diversity similar to the initial MI objective. For state-density estimation, we construct a novel conditional autoencoder with soft modularization for different skill policies in high-dimensional space. Meanwhile, to incentivize intra-skill exploration, we formulate an intrinsic reward based on the learned autoencoder that resembles count-based exploration in a compact latent space. Through extensive experiments in challenging state and image-based tasks, we find our method learns meaningful skills and achieves superior performance in various downstream tasks.
title Unsupervised Skill Discovery through Skill Regions Differentiation
topic Machine Learning
url https://arxiv.org/abs/2506.14420