Imagen de Portada

UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shah, Devan, Yang, Owen, Yang, Daniel, Zheng, Chongyi, Eysenbach, Benjamin
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning
por: Zheng, Chongyi, et al.
Publicado: (2024)

Contrastive Difference Predictive Coding
por: Zheng, Chongyi, et al.
Publicado: (2023)

Can We Really Learn One Representation to Optimize All Rewards?
por: Zheng, Chongyi, et al.
Publicado: (2026)

Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning
por: Reizinger, Patrik, et al.
Publicado: (2025)

Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making
por: Myers, Vivek, et al.
Publicado: (2024)

Intention-Conditioned Flow Occupancy Models
por: Zheng, Chongyi, et al.
Publicado: (2025)

Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization
por: Modirshanechi, Alireza, et al.
Publicado: (2026)

A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals
por: Liu, Grace, et al.
Publicado: (2024)

Value Flows
por: Dong, Perry, et al.
Publicado: (2025)

Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning
por: Yu, Xuehui, et al.
Publicado: (2024)

Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data
por: Zheng, Chongyi, et al.
Publicado: (2023)

Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration
por: Nimonkar, Chirayu, et al.
Publicado: (2025)

Horizon Generalization in Reinforcement Learning
por: Myers, Vivek, et al.
Publicado: (2025)

Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning
por: Yang, Hanlin, et al.
Publicado: (2024)

Skill-Critic: Refining Learned Skills for Hierarchical Reinforcement Learning
por: Hao, Ce, et al.
Publicado: (2023)

OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation
por: Yang, Haochen, et al.
Publicado: (2026)

SkillOrchestra: Learning to Route Agents via Skill Transfer
por: Wang, Jiayu, et al.
Publicado: (2026)

Is Temporal Difference Learning the Gold Standard for Stitching in RL?
por: Bortkiewicz, Michał, et al.
Publicado: (2025)

VendiRL: A Framework for Self-Supervised Reinforcement Learning of Diversely Diverse Skills
por: Lintunen, Erik M.
Publicado: (2025)

Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards
por: Mohamed, Faisal, et al.
Publicado: (2026)

Skill-R1: Agent Skill Evolution via Reinforcement Learning
por: Vishe, Yash, et al.
Publicado: (2026)

Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization
por: Li, Simin, et al.
Publicado: (2023)

Consistent Zero-Shot Imitation with Contrastive Goal Inference
por: Wantlin, Kathryn, et al.
Publicado: (2025)

ViReSkill: Vision-Grounded Replanning with Skill Memory for LLM-Based Planning in Lifelong Robot Learning
por: Kagaya, Tomoyuki, et al.
Publicado: (2025)

Choreographer: Learning and Adapting Skills in Imagination
por: Mazzaglia, Pietro, et al.
Publicado: (2022)

Learning Versatile Skills with Curriculum Masking
por: Tang, Yao, et al.
Publicado: (2024)

SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks
por: Wen, Yongyan, et al.
Publicado: (2024)

Skill Generalization with Verbs
por: Ma, Rachel, et al.
Publicado: (2024)

Skill Issues: An Analysis of CS:GO Skill Rating Systems
por: Bober-Irizar, Mikel, et al.
Publicado: (2024)

Iterative Deployment Improves Planning Skills in LLMs
por: Corrêa, Augusto B., et al.
Publicado: (2025)

Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning
por: Keller, Leon, et al.
Publicado: (2025)

A Rate-Distortion View of Uncertainty Quantification
por: Apostolopoulou, Ifigeneia, et al.
Publicado: (2024)

OGBench: Benchmarking Offline Goal-Conditioned RL
por: Park, Seohong, et al.
Publicado: (2024)

ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL
por: He, Zelin, et al.
Publicado: (2026)

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
por: Zhang, Haozhen, et al.
Publicado: (2026)

ComSD: Balancing Behavioral Quality and Diversity in Unsupervised Skill Discovery
por: Liu, Xin, et al.
Publicado: (2023)

Beyond Winning: Margin of Victory Relative to Expectation Unlocks Accurate Skill Ratings
por: Shorewala, Shivam, et al.
Publicado: (2025)

SUSD: Structured Unsupervised Skill Discovery through State Factorization
por: Hosseini, Seyed Mohammad Hadi, et al.
Publicado: (2026)

Behavior-Consistent Deep Reinforcement Learning
por: Hussing, Marcel, et al.
Publicado: (2026)

SLIM: Skill Learning with Multiple Critics
por: Emukpere, David, et al.
Publicado: (2024)