Image de couverture de livre

Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ni, Tianwei, Derman, Esther, Jain, Vineet, Taboga, Vincent, Ravanbakhsh, Siamak, Bacon, Pierre-Luc
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

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

Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity
par: Muni, Aneri, et autres
Publié: (2026)

The Three Regimes of Offline-to-Online Reinforcement Learning
par: Li, Lu, et autres
Publié: (2025)

Sampling from Energy-based Policies using Diffusion
par: Jain, Vineet, et autres
Publié: (2024)

On Diffusion Modeling for Anomaly Detection
par: Livernoche, Victor, et autres
Publié: (2023)

Discovery of Sustainable Refrigerants through Physics-Informed RL Fine-Tuning of Sequence Models
par: Goldszal, Adrien, et autres
Publié: (2025)

State Entropy Regularization for Robust Reinforcement Learning
par: Ashlag, Yonatan, et autres
Publié: (2025)

Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models
par: Jain, Vineet, et autres
Publié: (2025)

Understanding Behavioral Metric Learning: A Large-Scale Study on Distracting Reinforcement Learning Environments
par: Luo, Ziyan, et autres
Publié: (2025)

Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning
par: Jiralerspong, Marco, et autres
Publié: (2025)

Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning
par: Cho, Minjae, et autres
Publié: (2024)

Multi-Armed Sampling Problem and the End of Exploration
par: Pedramfar, Mohammad, et autres
Publié: (2025)

Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning
par: Song, Yeda, et autres
Publié: (2024)

Symmetry Breaking and Equivariant Neural Networks
par: Kaba, Sékou-Oumar, et autres
Publié: (2023)

Scaling Laws and Symmetry, Evidence from Neural Force Fields
par: Ngo, Khang, et autres
Publié: (2025)

Do Transformer World Models Give Better Policy Gradients?
par: Ma, Michel, et autres
Publié: (2024)

A Distributed ADMM-based Deep Learning Approach for Thermal Control in Multi-Zone Buildings under Demand Response Events
par: Taboga, Vincent, et autres
Publié: (2023)

Offline Reinforcement Learning with Universal Horizon Models
par: Chung, Hojun, et autres
Publié: (2026)

Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs
par: Shakerinava, Mehran, et autres
Publié: (2025)

On the Identifiability of Causal Abstractions
par: Li, Xiusi, et autres
Publié: (2025)

Rotation-Preserving Supervised Fine-Tuning
par: Jin, Hangzhan, et autres
Publié: (2026)

DyDiff: Long-Horizon Rollout via Dynamics Diffusion for Offline Reinforcement Learning
par: Zhao, Hanye, et autres
Publié: (2024)

The Expressive Limits of Diagonal SSMs for State-Tracking
par: Shakerinava, Mehran, et autres
Publié: (2026)

In-Context Reinforcement Learning through Bayesian Fusion of Context and Value Prior
par: Berkes, Anaïs, et autres
Publié: (2026)

Planning Transformer: Long-Horizon Offline Reinforcement Learning with Planning Tokens
par: Clinton, Joseph, et autres
Publié: (2024)

Horizon Reduction as Information Loss in Offline Reinforcement Learning
par: Nidadala, Uday Kumar, et autres
Publié: (2025)

Adaptive Coarse-to-Fine Subgoal Refinement for Long-Horizon Offline Goal-Conditioned Reinforcement Learning
par: Ke, Kaiqiang, et autres
Publié: (2026)

Bridging State and History Representations: Understanding Self-Predictive RL
par: Ni, Tianwei, et autres
Publié: (2024)

What Makes Value Learning Efficient in Residual Reinforcement Learning?
par: Ma, Guozheng, et autres
Publié: (2026)

Weight-Sharing Regularization
par: Shakerinava, Mehran, et autres
Publié: (2023)

Heterogeneous RBCs via Deep Multi-Agent Reinforcement Learning
par: Gabriele, Federico, et autres
Publié: (2025)

Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learning
par: Zhang, Jing, et autres
Publié: (2023)

Offline Learning and Forgetting for Reasoning with Large Language Models
par: Ni, Tianwei, et autres
Publié: (2025)

Symmetry-Aware Generative Modeling through Learned Canonicalization
par: Sareen, Kusha, et autres
Publié: (2025)

Robust Bandwidth Estimation for Real-Time Communication with Offline Reinforcement Learning
par: Kai, Jian, et autres
Publié: (2025)

Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
par: Ma, Guozheng, et autres
Publié: (2025)

Decoupling regularization from the action space
par: Mohammadpour, Sobhan, et autres
Publié: (2024)

Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
par: Mondal, Arnab Kumar, et autres
Publié: (2023)

Energy Loss Functions for Physical Systems
par: Kaba, Sékou-Oumar, et autres
Publié: (2025)

Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning
par: Castanyer, Roger Creus, et autres
Publié: (2025)