Imagen de Portada

Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Frauenknecht, Bernd, Eisele, Artur, Subhasish, Devdutt, Solowjow, Friedrich, Trimpe, Sebastian
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

On Rollouts in Model-Based Reinforcement Learning
por: Frauenknecht, Bernd, et al.
Publicado: (2025)

Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty
por: Eisele, Artur, et al.
Publicado: (2026)

Learning to Race in Minutes: Infoprop Dyna on the Mini Wheelbot
por: Subhasish, Devdutt, et al.
Publicado: (2026)

Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Space Models
por: Berger, Julia, et al.
Publicado: (2026)

Uncertainty-Aware Predictive Safety Filters for Probabilistic Neural Network Dynamics
por: Frauenknecht, Bernd, et al.
Publicado: (2026)

Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priors
por: Cramer, Emma, et al.
Publicado: (2024)

On the Consistency of Kernel Methods with Dependent Observations
por: Massiani, Pierre-François, et al.
Publicado: (2024)

On Foundation Models for Dynamical Systems from Purely Synthetic Data
por: Ziegler, Martin, et al.
Publicado: (2024)

Event-Triggered Time-Varying Bayesian Optimization
por: Brunzema, Paul, et al.
Publicado: (2022)

Sailing Towards Zero-Shot State Estimation using Foundation Models Combined with a UKF
por: Holtmann, Tobin, et al.
Publicado: (2025)

Safe Value Functions
por: Massiani, Pierre-François, et al.
Publicado: (2021)

Kernel conditional tests from learning-theoretic bounds
por: Massiani, Pierre-François, et al.
Publicado: (2025)

The Mini Wheelbot Dataset: High-Fidelity Data for Robot Learning
por: Hose, Henrik, et al.
Publicado: (2026)

Data-Driven Observability Analysis for Nonlinear Stochastic Systems
por: Massiani, Pierre-François, et al.
Publicado: (2023)

When Should a Language Model Trust Itself? Same-Model Self-Verification as a Conditional Confidence Signal
por: Phalod, Aditya Ajay
Publicado: (2026)

Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR
por: Wang, Tao, et al.
Publicado: (2026)

Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learning
por: Wimmer, Lisa, et al.
Publicado: (2025)

DiffusionRollout: Uncertainty-Aware Rollout Planning in Long-Horizon PDE Solving
por: Yoo, Seungwoo, et al.
Publicado: (2026)

Learning Hybrid Dynamics Models With Simulator-Informed Latent States
por: Ensinger, Katharina, et al.
Publicado: (2023)

MPX: Mixed Precision Training for JAX
por: Gräfe, Alexander, et al.
Publicado: (2025)

BayeSQP: Bayesian Optimization through Sequential Quadratic Programming
por: Brunzema, Paul, et al.
Publicado: (2026)

Bounded Exploration with World Model Uncertainty in Soft Actor-Critic Reinforcement Learning Algorithm
por: Qiao, Ting, et al.
Publicado: (2024)

Actor-Critic without Actor
por: Ki, Donghyeon, et al.
Publicado: (2025)

To Trust Or Not To Trust Your Vision-Language Model's Prediction
por: Dong, Hao, et al.
Publicado: (2025)

Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning
por: Ishfaq, Haque, et al.
Publicado: (2025)

Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuning
por: Krishnan, Ranganath, et al.
Publicado: (2024)

Trust, or Don't Predict: Introducing the CWSA Family for Confidence-Aware Model Evaluation
por: Shahnazari, Kourosh, et al.
Publicado: (2025)

From Uncertainty to Trust: Kernel Dropout for AI-Powered Medical Predictions
por: Azam, Ubaid, et al.
Publicado: (2024)

On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics
por: Nauman, Michal, et al.
Publicado: (2023)

Actor-Critic or Critic-Actor? A Tale of Two Time Scales
por: Bhatnagar, Shalabh, et al.
Publicado: (2022)

D2 Actor Critic: Diffusion Actor Meets Distributional Critic
por: Zhang, Lunjun, et al.
Publicado: (2025)

Actor-Critic Reinforcement Learning with Phased Actor
por: Wu, Ruofan, et al.
Publicado: (2024)

No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO
por: Moalla, Skander, et al.
Publicado: (2024)

In Trust We Survive: Emergent Trust Learning
por: Chen, Qianpu, et al.
Publicado: (2026)

Distributed Event-Based Learning via ADMM
por: Er, Guner Dilsad, et al.
Publicado: (2024)

Generative Actor Critic
por: Qin, Aoyang, et al.
Publicado: (2025)

Compressed Models are NOT Trust-equivalent to Their Large Counterparts
por: Rai, Rohit Raj, et al.
Publicado: (2025)

Evidential Trust-Aware Model Personalization in Decentralized Federated Learning for Wearable IoT
por: Rangwala, Murtaza, et al.
Publicado: (2025)

TRAM: Bridging Trust Regions and Sharpness Aware Minimization
por: Sherborne, Tom, et al.
Publicado: (2023)

Scaling Effects and Uncertainty Quantification in Neural Actor Critic Algorithms
por: Georgoudios, Nikos, et al.
Publicado: (2026)