Cover Image

ComSD: Balancing Behavioral Quality and Diversity in Unsupervised Skill Discovery

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Xin, Chen, Yaran, Zhao, Dongbin
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Artificial Intelligence Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning Future Representation with Synthetic Observations for Sample-efficient Reinforcement Learning
by: Liu, Xin, et al.
Published: (2024)

RoboGPT: an intelligent agent of making embodied long-term decisions for daily instruction tasks
by: Chen, Yaran, et al.
Published: (2023)

Unsupervised Skill Discovery as Exploration for Learning Agile Locomotion
by: Rho, Seungeun, et al.
Published: (2025)

From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Real-World Unsupervised Quality-Diversity
by: Grillotti, Luca, et al.
Published: (2025)

Unsupervised Skill Discovery for Robotic Manipulation through Automatic Task Generation
by: Jansonnie, Paul, et al.
Published: (2024)

Agentic Skill Discovery
by: Zhao, Xufeng, et al.
Published: (2024)

Cross-domain Random Pre-training with Prototypes for Reinforcement Learning
by: Liu, Xin, et al.
Published: (2023)

Identifying Selections for Unsupervised Subtask Discovery
by: Qiu, Yiwen, et al.
Published: (2024)

Neuro-Symbolic Skill Discovery for Conditional Multi-Level Planning
by: Aktas, Hakan, et al.
Published: (2024)

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

Vector Quantized-Elites: Unsupervised and Problem-Agnostic Quality-Diversity Optimization
by: Tsakonas, Constantinos, et al.
Published: (2025)

Offline Learning of Controllable Diverse Behaviors
by: Petitbois, Mathieu, et al.
Published: (2025)

Language Guided Skill Discovery
by: Rho, Seungeun, et al.
Published: (2024)

Skill Expansion and Composition in Parameter Space
by: Liu, Tenglong, et al.
Published: (2025)

Learning Human-Like Badminton Skills for Humanoid Robots
by: Chen, Yeke, et al.
Published: (2026)

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

Scaling Policy Gradient Quality-Diversity with Massive Parallelization via Behavioral Variations
by: Mitsides, Konstantinos, et al.
Published: (2025)

Group-Invariant Unsupervised Skill Discovery: Symmetry-aware Skill Representations for Generalizable Behavior
by: Chang, Junwoo, et al.
Published: (2026)

Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment
by: Petitbois, Mathieu, et al.
Published: (2026)

Skill Generalization with Verbs
by: Ma, Rachel, et al.
Published: (2024)

Is Diversity All You Need for Scalable Robotic Manipulation?
by: Shi, Modi, et al.
Published: (2025)

Unsupervised Learning of Effective Actions in Robotics
by: Zaric, Marko, et al.
Published: (2024)

InfoCon: Concept Discovery with Generative and Discriminative Informativeness
by: Liu, Ruizhe, et al.
Published: (2024)

Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length Adjustment
by: Choi, Jinwoo, et al.
Published: (2025)

Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning
by: Bettini, Matteo, et al.
Published: (2024)

Unsupervised Motion Retargeting for Human-Robot Imitation
by: Annabi, Louis, et al.
Published: (2024)

Skills Made to Order: Efficient Acquisition of Robot Cooking Skills Guided by Multiple Forms of Internet Data
by: Verghese, Mrinal, et al.
Published: (2024)

EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data
by: Zhang, Jesse, et al.
Published: (2024)

Learning Novel Skills from Language-Generated Demonstrations
by: Jin, Ao-Qun, et al.
Published: (2024)

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

Learning Parameterized Skills from Demonstrations
by: Gupta, Vedant, et al.
Published: (2025)

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

METRA: Scalable Unsupervised RL with Metric-Aware Abstraction
by: Park, Seohong, et al.
Published: (2023)

DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learning
by: Guo, Ke, et al.
Published: (2025)

MRS: Multi-Resolution Skills for HRL Agents
by: Sharma, Shashank, et al.
Published: (2025)

Offline Reinforcement Learning with Discrete Diffusion Skills
by: Qiao, RuiXi, et al.
Published: (2025)

Task-specific Subnetwork Discovery in Reinforcement Learning for Autonomous Underwater Navigation
by: Liu, Yi-Ling, et al.
Published: (2026)

Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning
by: Yunis, David, et al.
Published: (2023)

System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learning
by: Bettini, Matteo, et al.
Published: (2023)

Robust Policy Learning via Offline Skill Diffusion
by: Kim, Woo Kyung, et al.
Published: (2024)