Cover Image

Why long model-based rollouts are no reason for bad Q-value estimates

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wissmann, Philipp, Hein, Daniel, Udluft, Steffen, Tresp, Volker
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Is Q-learning an Ill-posed Problem?
by: Wissmann, Philipp, et al.
Published: (2025)

Model-based Offline Quantum Reinforcement Learning
by: Eisenmann, Simon, et al.
Published: (2024)

Learning Control Policies for Variable Objectives from Offline Data
by: Weber, Marc, et al.
Published: (2023)

Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations
by: Decker, Thomas, et al.
Published: (2025)

Neural-ANOVA: Analytical Model Decomposition using Automatic Integration
by: Limmer, Steffen, et al.
Published: (2024)

Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration
by: Decker, Thomas, et al.
Published: (2025)

To bootstrap or to rollout? An optimal and adaptive interpolation
by: Mou, Wenlong, et al.
Published: (2024)

First Experience with Real-Time Control Using Simulated VQC-Based Quantum Policies
by: Sun, Yize, et al.
Published: (2025)

TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning
by: Ormancı, Batıkan Bora, et al.
Published: (2024)

How the (Tensor-) Brain uses Embeddings and Embodiment to Encode Senses and Symbols
by: Tresp, Volker, et al.
Published: (2024)

FedPop: Federated Population-based Hyperparameter Tuning
by: Chen, Haokun, et al.
Published: (2023)

Quantum Architecture Search with Unsupervised Representation Learning
by: Sun, Yize, et al.
Published: (2024)

A Comparative Study on How Data Normalization Affects Zero-Shot Generalization in Time Series Foundation Models
by: Ahmed, Ihab, et al.
Published: (2025)

Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention
by: Koebler, Alexander, et al.
Published: (2025)

Temporal Fact Reasoning over Hyper-Relational Knowledge Graphs
by: Ding, Zifeng, et al.
Published: (2023)

Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance
by: Decker, Thomas, et al.
Published: (2024)

Multi-event Video-Text Retrieval
by: Zhang, Gengyuan, et al.
Published: (2023)

Bayes or Heisenberg: Who(se) Rules?
by: Tresp, Volker, et al.
Published: (2025)

Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model
by: Zhang, Jing, et al.
Published: (2024)

Routing-Free Mixture-of-Experts
by: Liu, Yilun, et al.
Published: (2026)

Agentic Neural Networks: Self-Evolving Multi-Agent Systems via Textual Backpropagation
by: Ma, Xiaowen, et al.
Published: (2025)

GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models
by: Liao, Ruotong, et al.
Published: (2023)

FedNano: Toward Lightweight Federated Tuning for Pretrained Multimodal Large Language Models
by: Zhang, Yao, et al.
Published: (2025)

LookupViT: Compressing visual information to a limited number of tokens
by: Koner, Rajat, et al.
Published: (2024)

Variational Quantum Circuits in Offline Contextual Bandit Problems
by: Schulte, Lukas, et al.
Published: (2025)

Entropy After </Think> for reasoning model early exiting
by: Wang, Xi, et al.
Published: (2025)

Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules
by: Liu, Yilun, et al.
Published: (2025)

PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model
by: Liu, Yilun, et al.
Published: (2024)

Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
by: Yan, Sikuan, et al.
Published: (2026)

Provably Better Explanations with Optimized Aggregation of Feature Attributions
by: Decker, Thomas, et al.
Published: (2024)

Model predictive control-based value estimation for efficient reinforcement learning
by: Wu, Qizhen, et al.
Published: (2023)

Q-value Regularized Transformer for Offline Reinforcement Learning
by: Hu, Shengchao, et al.
Published: (2024)

Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning
by: He, Pengfei, et al.
Published: (2024)

Neural topology optimization: the good, the bad, and the ugly
by: Sanu, Suryanarayanan Manoj, et al.
Published: (2024)

DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models
by: Ding, Zifeng, et al.
Published: (2024)

zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models
by: Ding, Zifeng, et al.
Published: (2023)

Universal approximation property of Banach space-valued random feature models including random neural networks
by: Neufeld, Ariel, et al.
Published: (2023)

Relational reasoning and inductive bias in transformers and large language models
by: Geerts, Jesse, et al.
Published: (2025)

The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective
by: Lin, Chi-Heng, et al.
Published: (2022)

Performance of AI agents based on reasoning language models on ALD process optimization tasks
by: Yanguas-Gil, Angel
Published: (2026)