Image de couverture de livre

TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bagatella, Marco, Pirotta, Matteo, Touati, Ahmed, Lazaric, Alessandro, Tirinzoni, Andrea
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

Simple Ingredients for Offline Reinforcement Learning
par: Cetin, Edoardo, et autres
Publié: (2024)

Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models
par: Tirinzoni, Andrea, et autres
Publié: (2025)

Temporal Difference Flows
par: Farebrother, Jesse, et autres
Publié: (2025)

Compositional Planning with Jumpy World Models
par: Farebrother, Jesse, et autres
Publié: (2026)

Fast Adaptation with Behavioral Foundation Models
par: Sikchi, Harshit, et autres
Publié: (2025)

Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model
par: Tarbouriech, Jean, et autres
Publié: (2026)

Reinforcement Learning with Options and State Representation
par: Ghriss, Ayoub, et autres
Publié: (2024)

Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities
par: Bagatella, Marco, et autres
Publié: (2026)

BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning
par: Li, Yitang, et autres
Publié: (2025)

Zero-Shot Offline Imitation Learning via Optimal Transport
par: Rupf, Thomas, et autres
Publié: (2024)

Maximum Entropy Semi-Supervised Inverse Reinforcement Learning
par: Audiffren, Julien, et autres
Publié: (2026)

Directed Exploration in Reinforcement Learning from Linear Temporal Logic
par: Bagatella, Marco, et autres
Publié: (2024)

AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling
par: Giral, Francisco, et autres
Publié: (2026)

Large-scale semi-supervised learning with online spectral graph sparsification
par: Calandriello, Daniele, et autres
Publié: (2026)

Analysis of Nystrom method with sequential ridge leverage scores
par: Calandriello, Daniele, et autres
Publié: (2026)

Pack only the essentials: Adaptive dictionary learning for kernel ridge regression
par: Calandriello, Daniele, et autres
Publié: (2026)

Test-time Offline Reinforcement Learning on Goal-related Experience
par: Bagatella, Marco, et autres
Publié: (2025)

On Zero-Shot Reinforcement Learning
par: Jeen, Scott
Publié: (2025)

DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning
par: Diaz-Bone, Leander, et autres
Publié: (2025)

A single algorithm for both restless and rested rotting bandits
par: Seznec, Julien, et autres
Publié: (2026)

Improved large-scale graph learning through ridge spectral sparsification
par: Calandriello, Daniele, et autres
Publié: (2026)

BRo-JEPA: Learning Modular Arithmetic in Latent Space
par: Jha, Divyansh, et autres
Publié: (2026)

Tackling the Zero-Shot Reinforcement Learning Loss Directly
par: Ollivier, Yann
Publié: (2025)

A Unified Framework for Zero-Shot Reinforcement Learning
par: Di Ventura, Jacopo, et autres
Publié: (2025)

Zero-Shot Instruction Following in RL via Structured LTL Representations
par: Giuri, Mattia, et autres
Publié: (2025)

CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining
par: Muhammad, Hada Melino, et autres
Publié: (2026)

Finer Behavioral Foundation Models via Auto-Regressive Features and Advantage Weighting
par: Cetin, Edoardo, et autres
Publié: (2024)

SMORE: Score Models for Offline Goal-Conditioned Reinforcement Learning
par: Sikchi, Harshit, et autres
Publié: (2023)

Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations
par: Slavutsky, Yuli, et autres
Publié: (2023)

Zero-Shot Instruction Following in RL via Structured LTL Representations
par: Jackermeier, Mathias, et autres
Publié: (2026)

Prediction and Causality of functional MRI and synthetic signal using a Zero-Shot Time-Series Foundation Model
par: Crimi, Alessandro, et autres
Publié: (2025)

SparseJEPA: Sparse Representation Learning of Joint Embedding Predictive Architectures
par: Hartman, Max, et autres
Publié: (2025)

Towards Robust Zero-Shot Reinforcement Learning
par: Zheng, Kexin, et autres
Publié: (2025)

BiJEPA: Bi-directional Joint Embedding Predictive Architecture for Symmetric Representation Learning
par: Huang, Yongchao
Publié: (2026)

System-2 Recommenders: Disentangling Utility and Engagement in Recommendation Systems via Temporal Point-Processes
par: Agarwal, Arpit, et autres
Publié: (2024)

Text-Conditional JEPA for Learning Semantically Rich Visual Representations
par: Huang, Chen, et autres
Publié: (2026)

ProteinJEPA: Latent prediction complements protein language models
par: Ofer, Dan, et autres
Publié: (2026)

Provable Zero-Shot Generalization in Offline Reinforcement Learning
par: Wang, Zhiyong, et autres
Publié: (2025)

Zero-Shot Reinforcement Learning Under Partial Observability
par: Jeen, Scott, et autres
Publié: (2025)

Zero-Shot Reinforcement Learning via Function Encoders
par: Ingebrand, Tyler, et autres
Publié: (2024)