Imagen de Portada

Priors Matter: Addressing Misspecification in Bayesian Deep Q-Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	van der Vaart, Pascal R., Yorke-Smith, Neil, Spaan, Matthijs T. J.
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

On the Equivalence of Random Network Distillation, Deep Ensembles, and Bayesian Inference
por: Zanger, Moritz A., et al.
Publicado: (2026)

Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model
por: Zanger, Moritz A., et al.
Publicado: (2025)

Twice Sequential Monte Carlo for Tree Search
por: Oren, Yaniv, et al.
Publicado: (2025)

Value Improved Actor Critic Algorithms
por: Oren, Yaniv, et al.
Publicado: (2024)

Universal Value-Function Uncertainties
por: Zanger, Moritz A., et al.
Publicado: (2025)

Explore-Go: Leveraging Exploration for Generalisation in Deep Reinforcement Learning
por: Weltevrede, Max, et al.
Publicado: (2024)

Diverse Projection Ensembles for Distributional Reinforcement Learning
por: Zanger, Moritz A., et al.
Publicado: (2023)

How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning
por: Weltevrede, Max, et al.
Publicado: (2025)

Positive Experience Reflection for Agents in Interactive Text Environments
por: Lippmann, Philip, et al.
Publicado: (2024)

Epistemic Monte Carlo Tree Search
por: Oren, Yaniv, et al.
Publicado: (2022)

Exploration Implies Data Augmentation: Reachability and Generalisation in Contextual MDPs
por: Weltevrede, Max, et al.
Publicado: (2024)

RecBayes: Recurrent Bayesian Ad Hoc Teamwork in Large Partially Observable Domains
por: Ribeiro, João G., et al.
Publicado: (2025)

Reinforcement Learning by Guided Safe Exploration
por: Yang, Qisong, et al.
Publicado: (2023)

Learning optimal objective values for MILP
por: Scavuzzo, Lara, et al.
Publicado: (2024)

VariBASed: Variational Bayes-Adaptive Sequential Monte-Carlo Planning for Deep Reinforcement Learning
por: de Vries, Joery A., et al.
Publicado: (2026)

Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks: An Extended Investigation
por: Schmitt, Marvin, et al.
Publicado: (2024)

Partial Identifiability and Misspecification in Inverse Reinforcement Learning
por: Skalse, Joar, et al.
Publicado: (2024)

Efficient Imitation under Misspecification
por: Espinosa-Dice, Nicolas, et al.
Publicado: (2025)

FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
por: Cinquin, Tristan, et al.
Publicado: (2024)

Towards Automated Self-Supervised Learning for Truly Unsupervised Graph Anomaly Detection
por: Li, Zhong, et al.
Publicado: (2025)

Pessimistic Iterative Planning with RNNs for Robust POMDPs
por: Galesloot, Maris F. L., et al.
Publicado: (2024)

Not All Explanations for Deep Learning Phenomena Are Equally Valuable
por: Jeffares, Alan, et al.
Publicado: (2025)

Causal Deep Learning
por: Berrevoets, Jeroen, et al.
Publicado: (2023)

Double Successive Over-Relaxation Q-Learning with an Extension to Deep Reinforcement Learning
por: R, Shreyas S
Publicado: (2024)

Online Incident Response Planning under Model Misspecification through Bayesian Learning and Belief Quantization
por: Hammar, Kim, et al.
Publicado: (2025)

Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch
por: Mechergui, Malek, et al.
Publicado: (2024)

Beyond Prior Limits: Addressing Distribution Misalignment in Particle Filtering
por: Shi, Yiwei, et al.
Publicado: (2025)

FlowQ: Energy-Guided Flow Policies for Offline Reinforcement Learning
por: Alles, Marvin, et al.
Publicado: (2025)

Simulation Priors for Data-Efficient Deep Learning
por: Treven, Lenart, et al.
Publicado: (2025)

Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning
por: Fang, Ronglong, et al.
Publicado: (2024)

In-Context Reinforcement Learning through Bayesian Fusion of Context and Value Prior
por: Berkes, Anaïs, et al.
Publicado: (2026)

Collapsed Inference for Bayesian Deep Learning
por: Zeng, Zhe, et al.
Publicado: (2023)

Is Elo Rating Reliable? A Study Under Model Misspecification
por: Tang, Shange, et al.
Publicado: (2025)

Position: The Future of Bayesian Prediction Is Prior-Fitted
por: Müller, Samuel, et al.
Publicado: (2025)

Bayesian Concept Bottleneck Models with LLM Priors
por: Feng, Jean, et al.
Publicado: (2024)

Large Language Models to Enhance Bayesian Optimization
por: Liu, Tennison, et al.
Publicado: (2024)

$β$-DQN: Improving Deep Q-Learning By Evolving the Behavior
por: Zhang, Hongming, et al.
Publicado: (2025)

Learning Distinguishable Representations in Deep Q-Networks for Linear Transfer
por: Sathish, Sooraj, et al.
Publicado: (2025)

Epistemic Traps: Rational Misalignment Driven by Model Misspecification
por: Xu, Xingcheng, et al.
Publicado: (2026)

Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond
por: Jeffares, Alan, et al.
Publicado: (2024)