Copertina

Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Goodall, Alexander W., Belardinelli, Francesco
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Approximate Model-Based Shielding for Safe Reinforcement Learning
di: Goodall, Alexander W., et al.
Pubblicazione: (2023)

Probabilistic Shielding for Safe Reinforcement Learning
di: Court, Edwin Hamel-De le, et al.
Pubblicazione: (2025)

Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments
di: Goodall, Alexander W., et al.
Pubblicazione: (2024)

Robust Shielding for Safe Reinforcement Learning
di: Court, Edwin Hamel-De le, et al.
Pubblicazione: (2026)

Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning
di: Goodall, Alexander W., et al.
Pubblicazione: (2025)

SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning
di: Anisimov, Maksim, et al.
Pubblicazione: (2026)

ProSh: Probabilistic Shielding for Model-free Reinforcement Learning
di: Court, Edwin Hamel-De le, et al.
Pubblicazione: (2025)

Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
di: Banerjee, Arko, et al.
Pubblicazione: (2024)

Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement Learning
di: Georgescu, Tiberiu-Andrei, et al.
Pubblicazione: (2025)

Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding
di: Bethell, Daniel, et al.
Pubblicazione: (2024)

Adaptive Shielding for Safe Reinforcement Learning under Hidden-Parameter Dynamics Shifts
di: Kwon, Minjae, et al.
Pubblicazione: (2025)

Robust Probabilistic Shielding for Safe Offline Reinforcement Learning
di: Galesloot, Maris F. L., et al.
Pubblicazione: (2026)

Verified Safe Reinforcement Learning for Neural Network Dynamic Models
di: Wu, Junlin, et al.
Pubblicazione: (2024)

Iterative Batch Reinforcement Learning via Safe Diversified Model-based Policy Search
di: Najib, Amna, et al.
Pubblicazione: (2024)

Overcoming Overfitting in Reinforcement Learning via Gaussian Process Diffusion Policy
di: Horprasert, Amornyos, et al.
Pubblicazione: (2025)

Explainable Reinforcement Learning for Formula One Race Strategy
di: Thomas, Devin, et al.
Pubblicazione: (2025)

Expressive Temporal Specifications for Reward Monitoring
di: Adalat, Omar, et al.
Pubblicazione: (2025)

Skill-based Safe Reinforcement Learning with Risk Planning
di: Zhang, Hanping, et al.
Pubblicazione: (2025)

Safe Reinforcement Learning for Real-World Engine Control
di: Bedei, Julian, et al.
Pubblicazione: (2025)

Oracle-Guided Soft Shielding for Safe Move Prediction in Chess
di: Rajendran, Prajit T, et al.
Pubblicazione: (2026)

Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation
di: Dai, Juntao, et al.
Pubblicazione: (2024)

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

Towards Fast Safe Online Reinforcement Learning via Policy Finetuning
di: Chen, Keru, et al.
Pubblicazione: (2024)

Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk
di: Ying, Chengyang, et al.
Pubblicazione: (2022)

Inverse Reinforcement Learning With Constraint Recovery
di: Das, Nirjhar, et al.
Pubblicazione: (2023)

Measuring Goal-Directedness
di: MacDermott, Matt, et al.
Pubblicazione: (2024)

Safe Urban Traffic Control via Uncertainty-Aware Conformal Prediction and World-Model Reinforcement Learning
di: Chandra, Joydeep, et al.
Pubblicazione: (2026)

Hierarchical Reinforcement Learning with Runtime Safety Shielding for Power Grid Operation
di: Malik, Gitesh
Pubblicazione: (2026)

Safe Learning Under Irreversible Dynamics via Asking for Help
di: Plaut, Benjamin, et al.
Pubblicazione: (2025)

Online Optimization for Offline Safe Reinforcement Learning
di: Chemingui, Yassine, et al.
Pubblicazione: (2025)

Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies
di: Tayal, Mumuksh, et al.
Pubblicazione: (2026)

Implicit Safe Set Algorithm for Provably Safe Reinforcement Learning
di: Zhao, Weiye, et al.
Pubblicazione: (2024)

Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
di: Ji, Jiaming, et al.
Pubblicazione: (2025)

Stable Deep Reinforcement Learning via Isotropic Gaussian Representations
di: Pasand, Ali Saheb, et al.
Pubblicazione: (2026)

Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model
di: Zheng, Yinan, et al.
Pubblicazione: (2024)

Enhance Exploration in Safe Reinforcement Learning with Contrastive Representation Learning
di: Doan, Duc Kien, et al.
Pubblicazione: (2025)

Safe Reinforcement Learning with Learned Non-Markovian Safety Constraints
di: Low, Siow Meng, et al.
Pubblicazione: (2024)

Sampling-Based Safe Reinforcement Learning
di: Vignola, Luca, et al.
Pubblicazione: (2026)

PNAct: Crafting Backdoor Attacks in Safe Reinforcement Learning
di: Guo, Weiran, et al.
Pubblicazione: (2025)

Offline Safe Reinforcement Learning Using Trajectory Classification
di: Gong, Ze, et al.
Pubblicazione: (2024)