Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning

Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning

International Conference on Learning Representations (ICLR), 2025

12 June 2025

Mykola Pechenizkiy

ArXiv (abs)PDF HTML

Papers citing "Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning"

6 / 6 papers shown

Title
VendiRL: A Framework for Self-Supervised Reinforcement Learning of Diversely Diverse Skills Erik M. Lintunen 147 1 0 03 Sep 2025
DETACH: Cross-domain Learning for Long-Horizon Tasks via Mixture of Disentangled Experts Yutong Shen Hangxu Liu Penghui Liu Ruizhe Xia Tianyi Yao Yitong Sun Tongtong Feng 123 4 0 11 Aug 2025
Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning Patrik Reizinger Bálint Mucsányi Siyuan Guo Benjamin Eysenbach Bernhard Schölkopf Wieland Brendel SSL 178 1 0 19 Jul 2025
AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification Geonwoo Cho Jaemoon Lee Jaegyun Im Subi Lee Jihwan Lee Sundong Kim 273 0 0 06 Jun 2025
Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent CooperationInternational Conference on Learning Representations (ICLR), 2025 Sicong Liu Yang Shu Chenjuan Guo Bin Yang OffRL 247 9 0 27 Mar 2025
Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of ExpertsInternational Conference on Machine Learning (ICML), 2024 Onur Celik Aleksandar Taranovic Gerhard Neumann 314 16 0 11 Mar 2024