Marco Favorito

Marco Favorito
Sapienza University of Rome | la sapienza · Department of Computer, Automatic and Management Engineering "Antonio Ruberti"

PhD Student in AI

About

17
Publications
592
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
33
Citations

Publications

Publications (17)
Preprint
Full-text available
Distributed Ledger Technologies (DLTs), when managed by a few trusted validators, require most but not all of the machinery available in public DLTs. In this work, we explore one possible way to profit from this state of affairs. We devise a combination of a modified Practical Byzantine Fault Tolerant (PBFT) protocol and a revised Flexible Round-Op...
Conference Paper
Synthesis techniques for temporal logic specifications are typically based on exploiting symbolic techniques, as done in model checking. These symbolic techniques typically use backward fixpoint computation. Planning, which can be seen as a specific form of synthesis, is a witness of the success of forward search approaches. In this paper, we devel...
Conference Paper
Datalog^E is the extension of Datalog with existential quantification. While its high expressive power, underpinned by a simple syntax and the support for full recursion, renders it particularly suitable for modern applications on Knowledge Graphs, query answering (QA) over such language is known to be undecidable in general. For this reason, diffe...
Preprint
We study temporally extended goals expressed in Pure-Past LTL (PPLTL). PPLTL is particularly interesting for expressing goals since it allows to express sophisticated tasks as in the Formal Methods literature, while the worst-case computational complexity of Planning in both deterministic and nondeterministic domains (FOND) remains the same as for...
Preprint
Datalog^E is the extension of Datalog with existential quantification. While its high expressive power, underpinned by a simple syntax and the support for full recursion, renders it particularly suitable for modern applications on knowledge graphs, query answering (QA) over such language is known to be undecidable in general. For this reason, diffe...
Article
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 unrelate...
Article
The translation from temporal logics to automata is the workhorse algorithm of several techniques in computer science and AI, such as reactive synthesis, reasoning about actions, FOND planning with temporal specifications, and reinforcement learning with non-Markovian rewards, to name a few. Unfortunately, the problem is computationally intractable...
Conference Paper
A common problem in Reinforcement Learning (RL) is that the reward function is hard to express. This can be overcome by resorting to Inverse Reinforcement Learning (IRL), which consists in first obtaining a reward function from a set of execution traces generated by an expert agent, and then making the learning agent learn the expert's behavior-thi...
Preprint
Full-text available
The heterogeneity of tools that support temporal logic formulae poses several challenges in terms of interoperability. This document proposes standard grammars for Linear Temporal Logic (LTL) (Pnueli 1977) and Linear Dynamic Logic (Vardi 2011; De Giacomo and Vardi 2013).
Conference Paper
In Markov Decision Processes (MDPs), rewards are assigned according to a function of the last state and action. This is often limiting, when the considered domain is not naturally Markovian, but becomes so after careful engineering of extended state space. The extended states record information from the past that is sufficient to assign rewards by...
Article
A common problem in Reinforcement Learning (RL) is that the reward function is hard to express. This can be overcome by resorting to Inverse Reinforcement Learning (IRL), which consists in first obtaining a reward function from a set of execution traces generated by an expert agent, and then making the learning agent learn the expert's behavior –th...
Article
In this work we have investigated the concept of “restraining bolt”, inspired by Science Fiction. We have two distinct sets of features extracted from the world, one by the agent and one by the authority imposing some restraining specifications on the behaviour of the agent (the “restraining bolt”). The two sets of features and, hence the model of...
Preprint
Full-text available
MDPs extended with LTLf/LDLf non-Markovian rewards have recently attracted interest as a way to specify rewards declaratively. In this paper, we discuss how a reinforcement learning agent can learn policies fulfilling LTLf/LDLf goals. In particular we focus on the case where we have two separate representations of the world: one for the agent, usin...

Network

Cited By