Author name cluster

Antonio Bucchiarone

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

ICAPS Conference 2020 Conference Paper

Learning Neural Search Policies for Classical Planning

Pawel Gomoluch
Dalal Alrajeh
Alessandra Russo
Antonio Bucchiarone

Heuristic forward search is currently the dominant paradigm in classical planning. Forward search algorithms typically rely on a single, relatively simple variation of best-first search and remain fixed throughout the process of solving a planning problem. Existing work combining multiple search techniques usually aims at supporting best-first search with an additional exploratory mechanism, triggered using a handcrafted criterion. A notable exception is very recent work which combines various search techniques using a trainable policy. That approach, however, is confined to a discrete action space comprising several fixed subroutines. In this paper, we introduce a parametrized search algorithm template which combines various search techniques within a single routine. The template's parameter space defines an infinite space of search algorithms, including, among others, BFS, local and random search. We then propose a neural architecture for designating the values of the search parameters given the state of the search. This enables expressing neural search policies that change the values of the parameters as the search progresses. The policies can be learned automatically, with the objective of maximizing the planner's performance on a given distribution of planning problems. We consider a training setting based on a stochastic optimization algorithm known as the cross-entropy method (CEM). Experimental evaluation of our approach shows that it is capable of finding effective distribution-specific search policies, outperforming the relevant baselines.

Details

TAAS Journal 2019 Journal Article

Collective Adaptation through Multi-Agents Ensembles

Antonio Bucchiarone

Modern software systems are becoming more and more socio-technical systems composed of distributed and heterogeneous agents from a mixture of people, their environment, and software components. These systems operate under continuous perturbations due to the unpredicted behaviors of people and the occurrence of exogenous changes in the environment. In this article, we introduce a notion of ensembles for which, systems with collective adaptability can be built as an emergent aggregation of autonomous and self-adaptive agents. Building upon this notion of ensemble, we present a distributed adaptation approach for systems composed by ensembles: collections of agents with their respective roles and goals. In these systems, adaptation is triggered by the run-time occurrence of an extraordinary circumstance, called issue. It is handled by an issue resolution process that involves agents affected by the issue to collaboratively adapt with minimal impact on their own preferences. Central to our approach is the implementation of a collective adaptation engine (CAE) able to solve issues in a collective fashion. The approach is instantiated in the context of a smart mobility scenario through which its main features are illustrated. To demonstrate the approach in action and evaluate it, we exploit the DeMOCAS framework, simulating the operation of an urban mobility scenario. We have executed a set of experiments with the goal to show how the CAE performs in terms of feasibility and scalability. With this approach, we are able to demonstrate how collective adaptation opens up new possibilities for tackling urban mobility challenges making it more sustainable respect to selfish and competitive behaviours.

Details DOI

AAMAS Conference 2018 Conference Paper

CARPooL: Collective Adaptation using concuRrent PLanning

Daniel Furelos-Blanco
Antonio Bucchiarone
Anders Jonsson

In this paper we present the CARPooL demonstrator, an implementation of a Collective Adaptation Engine (CAE) that addresses the challenge of collective adaptation in the smart mobility domain. CARPooL resolves adaptation issues via concurrent planning techniques. It also allows to interact with the provided solutions by adding new issues or analyzing the actions done by each agent.

PDF

AAMAS Conference 2018 Conference Paper

Collective Adaptation through Concurrent Planning: the Case of Sustainable Urban Mobility

Antonio Bucchiarone
Daniel Furelos-Blanco
Anders Jonsson
Fahmida Khandokar
Monjur Mourshed

In this paper we address the challenges that impede collective adaptation in smart mobility systems by proposing a notion of ensembles. Ensembles enable systems with collective adaptability to be built as emergent aggregations of autonomous and self-adaptive agents. Adaptation in these systems is triggered by a run-time occurrence, which is known as an issue. The novel aspect of our approach is, it allows agents affected by an issue in the context of a smart mobility scenario to adapt collaboratively with minimal impact on their own preferences through an issue resolution process based on concurrent planning algorithms.

PDF