Image de couverture de livre

SPoRt -- Safe Policy Ratio: Certified Training and Deployment of Task Policies in Model-Free RL

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cloete, Jacques, Vertovec, Nikolaus, Abate, Alessandro
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PlatoLTL: Learning to Generalize Across Symbols in LTL Instructions for Multi-Task RL
par: Cloete, Jacques, et autres
Publié: (2026)

Certified Neural Approximations of Nonlinear Dynamics
par: Mathiesen, Frederik Baymler, et autres
Publié: (2025)

Zero-Shot Instruction Following in RL via Structured LTL Representations
par: Jackermeier, Mathias, et autres
Publié: (2026)

Certified Approximate Reachability (CARe): Formal Error Bounds on Deep Learning of Reachable Sets
par: Solanki, Prashant, et autres
Publié: (2025)

Certifiably Robust Policies for Uncertain Parametric Environments
par: Schnitzer, Yannik, et autres
Publié: (2024)

Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagation
par: Vertovec, Nikolaus, et autres
Publié: (2025)

DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL
par: Jackermeier, Mathias, et autres
Publié: (2024)

Finite sample learning of moving targets
par: Vertovec, Nikolaus, et autres
Publié: (2024)

Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning
par: Melo, Luckeciano C., et autres
Publié: (2025)

SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
par: Wang, Chen, et autres
Publié: (2025)

Data-Driven Policy Mapping for Safe RL-based Energy Management Systems
par: Zangato, Theo, et autres
Publié: (2025)

Games for AI Control: Models of Safety Evaluations of AI Deployment Protocols
par: Griffin, Charlie, et autres
Publié: (2024)

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training
par: Fakoor, Rasool, et autres
Publié: (2026)

Zero-Shot Instruction Following in RL via Structured LTL Representations
par: Giuri, Mattia, et autres
Publié: (2025)

On the Limitations of Markovian Rewards to Express Multi-Objective, Risk-Sensitive, and Modal Tasks
par: Skalse, Joar, et autres
Publié: (2024)

When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
par: Hatgis-Kessell, Stephane, et autres
Publié: (2026)

SPoT: Subpixel Placement of Tokens in Vision Transformers
par: Hjelkrem-Tan, Martine, et autres
Publié: (2025)

Fat-to-Thin Policy Optimization: Offline RL with Sparse Policies
par: Zhu, Lingwei, et autres
Publié: (2025)

Soft Policy Optimization: Online Off-Policy RL for Sequence Models
par: Cohen, Taco, et autres
Publié: (2025)

Modular Diffusion Policy Training: Decoupling and Recombining Guidance and Diffusion for Offline RL
par: Chen, Zhaoyang, et autres
Publié: (2025)

Action-Free Offline-to-Online RL via Discretised State Policies
par: Neggatu, Natinael Solomon, et autres
Publié: (2026)

Residual Off-Policy RL for Finetuning Behavior Cloning Policies
par: Ankile, Lars, et autres
Publié: (2025)

SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data
par: Romeo, Carlo, et autres
Publié: (2026)

JaxRobotarium: Training and Deploying Multi-Robot Policies in 10 Minutes
par: Jain, Shalin Anand, et autres
Publié: (2025)

Policy Bifurcation in Safe Reinforcement Learning
par: Zou, Wenjun, et autres
Publié: (2024)

Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL
par: Sandhu, Dillon, et autres
Publié: (2026)

Inference Time Policy Optimization for Offline RL with Differentiable World Models
par: Deb, Rohan, et autres
Publié: (2026)

On-Policy RL with Optimal Reward Baseline
par: Hao, Yaru, et autres
Publié: (2025)

Partial Policy Gradients for RL in LLMs
par: Mathur, Puneet, et autres
Publié: (2026)

Decision-Point Guided Safe Policy Improvement
par: Sharma, Abhishek, et autres
Publié: (2024)

Training-Free Imitation Learning with Closed-Form Diffusion Policies
par: Mishra, Raghav, et autres
Publié: (2026)

Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning
par: Schnitzer, Yannik, et autres
Publié: (2026)

Safe Deep Policy Adaptation
par: Xiao, Wenli, et autres
Publié: (2023)

Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification
par: Skalse, Joar, et autres
Publié: (2024)

DeepSPoC: A Deep Learning-Based PDE Solver Governed by Sequential Propagation of Chaos
par: Du, Kai, et autres
Publié: (2024)

SNPL: Simultaneous Policy Learning and Evaluation for Safe Multi-Objective Policy Improvement
par: Cho, Brian, et autres
Publié: (2025)

CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies
par: Cho, Brian M, et autres
Publié: (2024)

Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies
par: Lee, Haanvid, et autres
Publié: (2024)

Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training
par: Mroueh, Youssef, et autres
Publié: (2025)

SafeAR: Safe Algorithmic Recourse by Risk-Aware Policies
par: Wu, Haochen, et autres
Publié: (2023)