Copertina

Stable and Safe Human-aligned Reinforcement Learning through Neural Ordinary Differential Equations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhao, Liqun, Miao, Keyan, Gatsis, Konstantinos, Papachristodoulou, Antonis
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Robotics Systems and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Opt-ODENet: A Neural ODE Framework with Differentiable QP Layers for Safe and Stable Control Design (longer version)
di: Miao, Keyan, et al.
Pubblicazione: (2025)

Constrained Diffusers for Safe Planning and Control
di: Zhang, Jichen, et al.
Pubblicazione: (2025)

Learning Neural Controllers with Optimality and Stability Guarantees Using Input-Output Dissipativity
di: Wang, Han, et al.
Pubblicazione: (2025)

Safe Reinforcement Learning with Minimal Supervision
di: Quessy, Alexander, et al.
Pubblicazione: (2025)

Safe Neural Control for Non-Affine Control Systems with Differentiable Control Barrier Functions
di: Xiao, Wei, et al.
Pubblicazione: (2023)

Towards Safe Learning-Based Non-Linear Model Predictive Control through Recurrent Neural Network Modeling
di: Clement, Mihaela-Larisa, et al.
Pubblicazione: (2026)

Deep Reinforcement Learning with Enhanced PPO for Safe Mobile Robot Navigation
di: Taheri, Hamid, et al.
Pubblicazione: (2024)

Risk-Aware Safe Reinforcement Learning for Control of Stochastic Linear Systems
di: Esmaeili, Babak, et al.
Pubblicazione: (2025)

System-level Safety Guard: Safe Tracking Control through Uncertain Neural Network Dynamics Models
di: Li, Xiao, et al.
Pubblicazione: (2023)

Learning Coverage Paths in Unknown Environments with Deep Reinforcement Learning
di: Jonnarth, Arvi, et al.
Pubblicazione: (2023)

Real-Time Safe Control of Neural Network Dynamic Models with Sound Approximation
di: Hu, Hanjiang, et al.
Pubblicazione: (2024)

Towards a Practical Understanding of Lagrangian Methods in Safe Reinforcement Learning
di: Spoor, Lindsay, et al.
Pubblicazione: (2025)

Learning Stable and Passive Neural Differential Equations
di: Cheng, Jing, et al.
Pubblicazione: (2024)

ABNet: Attention BarrierNet for Safe and Scalable Robot Learning
di: Xiao, Wei, et al.
Pubblicazione: (2024)

CN-CBF: Composite Neural Control Barrier Function for Safe Robot Navigation in Dynamic Environments
di: Derajić, Bojan, et al.
Pubblicazione: (2026)

Safe and Stable Filter Design Using a Relaxed Compatibitlity Control Barrier -- Lyapunov Condition
di: Wang, Han, et al.
Pubblicazione: (2024)

Safe Control using Learned Safety Filters and Adaptive Conformal Inference
di: Huriot, Sacha, et al.
Pubblicazione: (2026)

Safe and Near-Optimal Control with Online Dynamics Learning
di: Prajapat, Manish, et al.
Pubblicazione: (2025)

Safe Value Functions
di: Massiani, Pierre-François, et al.
Pubblicazione: (2021)

GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model
di: Zhou, Zhehua, et al.
Pubblicazione: (2024)

Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning
di: Jonnarth, Arvi, et al.
Pubblicazione: (2024)

Learning to Coordinate: Distributed Meta-Trajectory Optimization Via Differentiable ADMM-DDP
di: Wang, Bingheng, et al.
Pubblicazione: (2025)

Learning a Stable, Safe, Distributed Feedback Controller for a Heterogeneous Platoon of Autonomous Vehicles
di: Shaham, Michael H., et al.
Pubblicazione: (2024)

Learning Maximal Safe Sets Using Hypernetworks for MPC-based Local Trajectory Planning in Unknown Environments
di: Derajić, Bojan, et al.
Pubblicazione: (2024)

Active Alignments of Lens Systems with Reinforcement Learning
di: Burkhardt, Matthias, et al.
Pubblicazione: (2025)

Off Policy Lyapunov Stability in Reinforcement Learning
di: Gill, Sarvan, et al.
Pubblicazione: (2025)

A Safe Reinforcement Learning driven Weights-varying Model Predictive Control for Autonomous Vehicle Motion Control
di: Zarrouki, Baha, et al.
Pubblicazione: (2024)

Meta SAC-Lag: Towards Deployable Safe Reinforcement Learning via MetaGradient-based Hyperparameter Tuning
di: Honari, Homayoun, et al.
Pubblicazione: (2024)

Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers
di: Shen, Keyi, et al.
Pubblicazione: (2026)

A Prototyping Framework for Distributed Control of Multi-Robot Systems
di: Memon, Junaid Ahmed, et al.
Pubblicazione: (2026)

Data-Driven Permissible Safe Control with Barrier Certificates
di: Mazouz, Rayan, et al.
Pubblicazione: (2024)

Enhancing Safety in Mixed Traffic: Learning-Based Modeling and Efficient Control of Autonomous and Human-Driven Vehicles
di: Wang, Jie, et al.
Pubblicazione: (2024)

Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey
di: Ganai, Milan, et al.
Pubblicazione: (2024)

Provably Optimal Reinforcement Learning under Safety Filtering
di: Oh, Donggeon David, et al.
Pubblicazione: (2025)

Safe Guaranteed Exploration for Non-linear Systems
di: Prajapat, Manish, et al.
Pubblicazione: (2024)

Adaptive Gain Scheduling using Reinforcement Learning for Quadcopter Control
di: Timmerman, Mike, et al.
Pubblicazione: (2024)

Goal Reaching with Eikonal-Constrained Hierarchical Quasimetric Reinforcement Learning
di: Giammarino, Vittorio, et al.
Pubblicazione: (2025)

Constraint-Aware Reinforcement Learning via Adaptive Action Scaling
di: Dawood, Murad, et al.
Pubblicazione: (2025)

SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning
di: Huang, Tzu-Yuan, et al.
Pubblicazione: (2025)

Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis
di: Hafez, Ahmad, et al.
Pubblicazione: (2025)