paper-with-me

Papers

Formally Verified Solution Methods for Infinite-Horizon Markov Decision Processes

2022-06-05 · Maximilian Schäfeller, Mohammad Abdulaziz

We formally verify executable algorithms for solving Markov decision processes (MDPs) in the interactive theorem prover Isabelle/HOL. We build on existing formalizations of probability theory to analyze the expected total reward criterion on infinite-horizon problems. Our developments formalize the Bellman equation and give conditions under which optimal policies exist. Based on this analysis, we verify dynamic programming algorithms to solve tabular MDPs. We evaluate the formally verified implementations experimentally on standard problems and show they are practical. Furthermore, we show that, combined with efficient unverified implementations, our system can compete with and even outperform state-of-the-art systems.

📄 PDF Abstract BibTeX arXiv:2206.02169

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Deriving time-averaged active inference from control principles

2022-08-22 · Eli Sennesh, Jordan Theriault, Jan-Willem van de Meent, Lisa Feldman Barrett 외

Active inference offers a principled account of behavior as minimizing average sensory surprise over time. Applications of active inference to control problems have heretofore tended to focus on finite-horizon or discoun…

Verified Safe Reinforcement Learning for Neural Network Dynamic Models

2024-05-25 · Junlin Wu, huan zhang, Yevgeniy Vorobeychik

Learning reliably safe autonomous control is one of the core problems in trustworthy autonomy. However, training a controller that can be formally verified to be safe remains a major challenge. We introduce a novel appro…

reinforcement-learningReinforcement LearningSafe Reinforcement Learning

Of Good Demons and Bad Angels: Guaranteeing Safe Control under Finite Precision

2025-07-30 · Samuel Teuber, Debasmita Lohar, Bernhard Beckert arxiv

As neural networks (NNs) become increasingly prevalent in safety-critical neural network-controlled cyber-physical systems (NNCSs), formally guaranteeing their safety becomes crucial. For these systems, safety must be en…

Formally Verified SAT-Based AI Planning

2020-10-27 · Mohammad Abdulaziz, Friedrich Kurz

We present an executable formally verified SAT encoding of classical AI planning. We use the theorem prover Isabelle/HOL to perform the verification. We experimentally test the verified encoding and show that it can be u…

Structural Equivalence and Learning Dynamics in Delayed MARL

2026-05-05 · Jules Sintes, Ana Bušić, Jiamin Zhu arxiv

We formally establish the equivalence between Observation Delay (OD) and Action Delay (AD) in cooperative partially observable multi-agent systems using observation-action histories. We show that both systems generate id…