paper-with-me

홈 › Papers

Runtime Verification of Learning Properties for Reinforcement Learning Algorithms

2023-11-16 · Tommaso Mannucci, Julio de Oliveira Filho

Reinforcement learning (RL) algorithms interact with their environment in a trial-and-error fashion. Such interactions can be expensive, inefficient, and timely when learning on a physical system rather than in a simulation. This work develops new runtime verification techniques to predict when the learning phase has not met or will not meet qualitative and timely expectations. This paper presents three verification properties concerning the quality and timeliness of learning in RL algorithms. With each property, we propose design steps for monitoring and assessing the properties during the system's operation.

📄 PDF Abstract BibTeX arXiv:2311.09811

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

A Mixed Integer Programming Approach for Verifying Properties of Binarized Neural Networks

2022-03-11 · Christopher Lazarus, Mykel J. Kochenderfer

Many approaches for verifying input-output properties of neural networks have been proposed recently. However, existing algorithms do not scale well to large networks. Recent work in the field of model compression studie…

Collision AvoidanceModel Compression

Towards Partial Monitoring: It is Always too Soon to Give Up

2021-10-25 · Angelo Ferrando, Rafael C. Cardoso

Runtime Verification is a lightweight formal verification technique. It is used to verify at runtime whether the system under analysis behaves as expected. The expected behaviour is usually formally specified by means of…

MPBMC: Multi-Property Bounded Model Checking with GNN-guided Clustering

2026-02-26 · Soumik Guha Roy, Sumana Ghosh, Ansuman Banerjee, Raj Kumar Gajavelly 외 arxiv

Formal verification of designs with multiple properties has been a long-standing challenge for the verification research community. The task of coming up with an effective strategy that can efficiently cluster properties…

Graph Neural Network

Learning Verifiable Control Policies Using Relaxed Verification

2025-04-23 · Puja Chaudhury, Alexander Estornell, Michael Everett

To provide safety guarantees for learning-based control systems, recent work has developed formal verification methods to apply after training ends. However, if the trained policy does not meet the specifications, or the…

Deep Binary Reinforcement Learning for Scalable Verification

2022-03-11 · Christopher Lazarus, Mykel J. Kochenderfer

The use of neural networks as function approximators has enabled many advances in reinforcement learning (RL). The generalization power of neural networks combined with advances in RL algorithms has reignited the field o…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)