paper-with-me

홈 › Papers

Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specifications

2018-07-17 · Giuseppe De Giacomo, Luca Iocchi, Marco Favorito, Fabio Patrizi

In this work we investigate on the concept of "restraining bolt", envisioned in Science Fiction. Specifically we introduce a novel problem in AI. We have two distinct sets of features extracted from the world, one by the agent and one by the authority imposing restraining specifications (the "restraining bolt"). The two sets are apparently unrelated since of interest to independent parties, however they both account for (aspects of) the same world. We consider the case in which the agent is a reinforcement learning agent on the first set of features, while the restraining bolt is specified logically using linear time logic on finite traces LTLf/LDLf over the second set of features. We show formally, and illustrate with examples, that, under general circumstances, the agent can learn while shaping its goals to suitably conform (as much as possible) to the restraining bolt specifications.

📄 PDF Abstract BibTeX arXiv:1807.06333

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

LTLf and LDLf Monitoring: A Technical Report

2014-04-30 · Giuseppe De Giacomo, Riccardo De Masellis, Marco Grasso, Fabrizio Maggi 외

Runtime monitoring is one of the central tasks to provide operational decision support to running business processes, and check on-the-fly whether they comply with constraints and rules. We study runtime monitoring of pr…

Translation

A Deep Learning Approach to Identify Rock Bolts in Complex 3D Point Clouds of Underground Mines Captured Using Mobile Laser Scanners

2025-06-25 · Dibyayan Patra, Pasindu Ranasinghe, Bikram Banerjee, Simit Raval

Rock bolts are crucial components of the subterranean support systems in underground mines that provide adequate structural reinforcement to the rock mass to prevent unforeseen hazards like rockfalls. This makes frequent…

Feature EngineeringSemantic Segmentation

Planning and Synthesis Under Assumptions

2018-07-18 · Benjamin Aminof, Giuseppe De Giacomo, Aniello Murano, Sasha Rubin

In Reasoning about Action and Planning, one synthesizes the agent plan by taking advantage of the assumption on how the environment works (that is, one exploits the environment's effects, its fairness, its trajectory con…

Fairness

Time to Reason: Scalable Neurosymbolic Learning for LTLf via Fuzzy Semantics

2026-08-17 · Riccardo Andreoni, Andrei Buliga, Alessandro Daniele, Paolo Felli 외 arxiv

Neurosymbolic (NeSy) Artificial Intelligence aims to integrate Deep Learning (DL) architectures with symbolic reasoning. While initial NeSy approaches have targeted mainly symbolic reasoning in propositional and first-or…

Multi-Player Games with LDL Goals over Finite Traces

2020-08-13 · Julian Gutierrez, Giuseppe Perelli, Michael Wooldridge

Linear Dynamic Logic on finite traces LDLf is a powerful logic for reasoning about the behaviour of concurrent and multi-agent systems. In this paper, we investigate techniques for both the characterisation and verificat…