Image de couverture de livre

Observations Meet Actions: Learning Control-Sufficient Representations for Robust Policy Generalization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gu, Yuliang, Cao, Hongpeng, Caccamo, Marco, Hovakimyan, Naira
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Bregman Centroid Guided Cross-Entropy Method
par: Gu, Yuliang, et autres
Publié: (2025)

Proto-MPC: An Encoder-Prototype-Decoder Approach for Quadrotor Control in Challenging Winds
par: Gu, Yuliang, et autres
Publié: (2024)

Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings
par: Cao, Hongpeng, et autres
Publié: (2023)

Physics-model-guided Worst-case Sampling for Safe Reinforcement Learning
par: Cao, Hongpeng, et autres
Publié: (2024)

A Robust Task-Level Control Architecture for Learned Dynamical Systems
par: Pathak, Eshika, et autres
Publié: (2025)

Robust Model Based Reinforcement Learning Using $\mathcal{L}_1$ Adaptive Control
par: Sung, Minjun, et autres
Publié: (2024)

Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning
par: Theile, Mirco, et autres
Publié: (2024)

Simplex-enabled Safe Continual Learning Machine
par: Cao, Hongpeng, et autres
Publié: (2024)

Perception Simplex: Verifiable Collision Avoidance in Autonomous Vehicles Amidst Obstacle Detection Faults
par: Bansal, Ayoosh, et autres
Publié: (2022)

Distributionally Robust Imitation Learning: Layered Control Architecture for Certifiable Autonomy
par: Gahlawat, Aditya, et autres
Publié: (2025)

Learning to Generate All Feasible Actions
par: Theile, Mirco, et autres
Publié: (2023)

Action-Sufficient Goal Representations
par: Hyeon, Jinu, et autres
Publié: (2026)

Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement Learning
par: Trumpp, Raphael, et autres
Publié: (2026)

Guaranteed Trajectory Tracking under Learned Dynamics with Contraction Metrics and Disturbance Estimation
par: Zhao, Pan, et autres
Publié: (2021)

Action Mapping for Reinforcement Learning in Continuous Environments with Constraints
par: Theile, Mirco, et autres
Publié: (2024)

Towards a Robust Retrieval-Based Summarization System
par: Liu, Shengjie, et autres
Publié: (2024)

Learning Tube-Certified Control using Robust Contraction Metrics
par: Sharma, Vivek, et autres
Publié: (2023)

Residual-based Language Models are Free Boosters for Biomedical Imaging
par: Lai, Zhixin, et autres
Publié: (2024)

Fair Sufficient Representation Learning
par: Zhou, Xueyu, et autres
Publié: (2025)

Impoola: The Power of Average Pooling for Image-Based Deep Reinforcement Learning
par: Trumpp, Raphael, et autres
Publié: (2025)

Learning to Recharge: UAV Coverage Path Planning through Deep Reinforcement Learning
par: Theile, Mirco, et autres
Publié: (2023)

Task-Parameter Nexus: Task-Specific Parameter Learning for Model-Based Control
par: Cheng, Sheng, et autres
Publié: (2024)

The New Agronomists: Language Models are Experts in Crop Management
par: Wu, Jing, et autres
Publié: (2024)

Estimating Conditional Average Treatment Effects via Sufficient Representation Learning
par: Shi, Pengfei, et autres
Publié: (2024)

Synergistic Simplex: Cooperative Runtime Assurance for Safety-Critical Autonomous Systems
par: Bansal, Ayoosh, et autres
Publié: (2026)

MEASURE: Multi-scale Minimal Sufficient Representation Learning for Domain Generalization in Sleep Staging
par: Jo, Sangmin, et autres
Publié: (2025)

Boosting Deep Ensembles with Learning Rate Tuning
par: Jin, Hongpeng, et autres
Publié: (2024)

Robust Offline Policy Learning with Observational Data from Multiple Sources
par: Carranza, Aldo Gael, et autres
Publié: (2024)

Data-Centric Machine Learning for Earth Observation: Necessary and Sufficient Features
par: Najjar, Hiba, et autres
Publié: (2024)

Seeking the Sufficiency and Necessity Causal Features in Multimodal Representation Learning
par: Chen, Boyu, et autres
Publié: (2024)

Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning
par: Li, Zijian, et autres
Publié: (2025)

GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning
par: Ding, Shutong, et autres
Publié: (2025)

Action Robust Reinforcement Learning via Optimal Adversary Aware Policy Optimization
par: Nie, Buqing, et autres
Publié: (2025)

Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness
par: Tian, Ye, et autres
Publié: (2023)

Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?
par: Ibrahim, Mark, et autres
Publié: (2024)

Deep Fair Learning: A Unified Framework for Fine-tuning Representations with Sufficient Networks
par: Shi, Enze, et autres
Publié: (2025)

Dual Action Policy for Robust Sim-to-Real Reinforcement Learning
par: Terence, Ng Wen Zheng, et autres
Publié: (2024)

Beyond Observations: Reconstruction Error-Guided Irregularly Sampled Time Series Representation Learning
par: Liu, Jiexi, et autres
Publié: (2025)

Distributionally Robust Policy Evaluation and Learning for Continuous Treatment with Observational Data
par: Leung, Cheuk Hang, et autres
Publié: (2025)

Polynomial Width is Sufficient for Set Representation with High-dimensional Features
par: Wang, Peihao, et autres
Publié: (2023)