Image de couverture de livre

Learning from Demonstrations via Capability-Aware Goal Sampling

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Duan, Yuanlin, Wang, Yuning, Qiu, Wenjie, Zhu, He
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Learning World Models for Unconstrained Goal Navigation
par: Duan, Yuanlin, et autres
Publié: (2024)

Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning
par: Duan, Yuanlin, et autres
Publié: (2024)

DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Demonstration and Reasoning
par: Qiu, Hongye, et autres
Publié: (2025)

Learning Goal-oriented Bimanual Dough Rolling Using Dynamic Heterogeneous Graph Based on Human Demonstration
par: Liu, Junjia, et autres
Publié: (2024)

VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL
par: Hu, Zengjie, et autres
Publié: (2025)

Imitation Learning from Suboptimal Demonstrations via Meta-Learning An Action Ranker
par: Fan, Jiangdong, et autres
Publié: (2024)

ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learning
par: Kim, Byung-ju, et autres
Publié: (2025)

Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training
par: Gu, Jihao, et autres
Publié: (2025)

Demonstrating the Continual Learning Capabilities and Practical Application of Discrete-Time Active Inference
par: Prakki, Rithvik
Publié: (2024)

Decoupled Hierarchical Reinforcement Learning with State Abstraction for Discrete Grids
par: Xiao, Qingyu, et autres
Publié: (2025)

D-Shape: Demonstration-Shaped Reinforcement Learning via Goal Conditioning
par: Wang, Caroline, et autres
Publié: (2022)

A Modular Dataset to Demonstrate LLM Abstraction Capability
par: Atanas, Adam, et autres
Publié: (2025)

GCHR : Goal-Conditioned Hindsight Regularization for Sample-Efficient Reinforcement Learning
par: Lei, Xing, et autres
Publié: (2025)

Sample-Efficient Reinforcement Learning with Symmetry-Guided Demonstrations for Robotic Manipulation
par: Enayati, Amir M. Soufi, et autres
Publié: (2023)

Demonstration Selection for In-Context Learning via Reinforcement Learning
par: Wang, Xubin, et autres
Publié: (2024)

When a Robot is More Capable than a Human: Learning from Constrained Demonstrators
par: Li, Xinhu, et autres
Publié: (2025)

Small Shifts, Large Gains: Unlocking Traditional TSP Heuristic Guided-Sampling via Unsupervised Neural Instance Modification
par: Huang, Wei, et autres
Publié: (2026)

Learning to Reach Goals via Diffusion
par: Jain, Vineet, et autres
Publié: (2023)

Comparable Demonstrations are Important in In-Context Learning: A Novel Perspective on Demonstration Selection
par: Fan, Caoyun, et autres
Publié: (2023)

DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization
par: Xie, Xuan, et autres
Publié: (2025)

Goal Exploration via Adaptive Skill Distribution for Goal-Conditioned Reinforcement Learning
par: Wu, Lisheng, et autres
Publié: (2024)

Cognitive-Level Adaptive Generation via Capability-Aware Retrieval and Style Adaptation
par: Wang, Qingsong, et autres
Publié: (2025)

Position: Capability Control Should be a Separate Goal From Alignment
par: Siddiqui, Shoaib Ahmed, et autres
Publié: (2026)

Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning
par: Tao, Stone, et autres
Publié: (2024)

Escaping the Verifier: Learning to Reason via Demonstrations
par: Cai, Locke, et autres
Publié: (2025)

TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations
par: Bae, Junik, et autres
Publié: (2024)

Learning Novel Skills from Language-Generated Demonstrations
par: Jin, Ao-Qun, et autres
Publié: (2024)

Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning
par: Guo, Weiyang, et autres
Publié: (2025)

Learning from Active Human Involvement through Proxy Value Propagation
par: Peng, Zhenghao, et autres
Publié: (2025)

Active Constraint Learning in High Dimensions from Demonstrations
par: Qiu, Zheng, et autres
Publié: (2025)

When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning
par: Qiu, Chenghao, et autres
Publié: (2026)

A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration
par: Cui, Yingqian, et autres
Publié: (2024)

Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy
par: Zhang, Xiaoyun, et autres
Publié: (2025)

Reaching Consensus in Cooperative Multi-Agent Reinforcement Learning with Goal Imagination
par: Wang, Liangzhou, et autres
Publié: (2024)

1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
par: Wang, Kevin, et autres
Publié: (2025)

Learning to Ground Existentially Quantified Goals
par: Funkquist, Martin, et autres
Publié: (2024)

GRAML: Goal Recognition As Metric Learning
par: Shamir, Matan, et autres
Publié: (2025)

Goal-Conditioned Decision Transformer for Multi-Goal Offline Reinforcement Learning
par: Gajewski, Paweł, et autres
Publié: (2024)

Learning Reasoning Rewards from Expert Demonstrations with Inverse Reinforcement Learning
par: Fanconi, Claudio, et autres
Publié: (2025)

Subtask-Aware Visual Reward Learning from Segmented Demonstrations
par: Kim, Changyeon, et autres
Publié: (2025)