Publications

In evidence

(For a full list see below)

Explainable Inference on Sequential Data via Memory-Tracking

We propose an approach to build explanations for sequential tasks exploiting the memory reading and writing operations of Memory Augumented Neural Networks.

Biagio La Rosa, Roberto Capobianco and Daniele Nardi

Paper   Code   BibTeX   Blog Post

@inproceedings{LaRosa20,
title = {Explainable Inference on Sequential Data via Memory-Tracking},
author = {La Rosa, Biagio and Capobianco, Roberto and Nardi, Daniele},
booktitle = {Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
pages = {2006--2013},
year = {2020},
month = {7},
doi = {10.24963/ijcai.2020/278},
url = {https://doi.org/10.24963/ijcai.2020/278},
}

 

Full List

2022
Grounding LTLf Specifications in Images.
Elena Umili, Roberto Capobianco and Giuseppe De Giacomo.
Workshop on Neural-Symbolic Learning and Reasoning.
Paper   Code   BibTeX  
        @inproceedings{umili2022,
author = {Elena Umili and Roberto Capobianco and Giuseppe {De Giacomo}},
title = {Grounding LTLf Specifications in Images},
booktitle = {16th International Workshop on Neural-Symbolic Learning and Reasoning},
year = {2022}, }
A self-interpretable module for deep image classification on small data.
Biagio La Rosa, Roberto Capobianco and Daniele Nardi.
Applied Intelligence Journal.
Paper   Code   BibTeX  
        @Article{LaRosa2022,
author = {Biagio La Rosa and Roberto Capobianco and Daniele Nardi},
journal = {Applied Intelligence},
title = {A self-interpretable module for deep image classification on small data},
year = {2022},
month = {aug},
doi = {10.1007/s10489-022-03886-6},
publisher = {Springer Science and Business Media {LLC}},
}
2021
Learning a Symbolic Planning Domain through the Interaction with Continuous Environments.
Elena Umili, Emanuele Antonioni, Francesco Riccio, Roberto Capobianco, Daniele Nardi and Giuseppe De Giacomo.
Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning ({PRL}).
Paper   BibTeX  
        @inproceedings{umili2021,
author = {Elena Umili and Emanuele Antonioni and Francesco Riccio and
Roberto Capobianco and Daniele Nardi and Giuseppe {De Giacomo}},
title = {Learning a Symbolic Planning Domain through the Interaction with Continuous Environments},
booktitle = {Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning ({PRL})},
year = {2021},
}
Molecule Generation from Input-Attributions over Graph Convolutional Networks.
Dylan Savoia, Alessio Ragno, Roberto Capobianco.
ELLIS Machine Learning for Molecules workshop (ML4Molecules).
Paper   BibTeX  
        @Article{Savoia2022,
author = {Dylan Savoia and Alessio Ragno and Roberto Capobianco},
journal = {ELLIS Machine Learning for Molecules workshop (ML4Molecules) 2021},
title = {Molecule Generation from Input-Attributions over Graph Convolutional Networks},
year = {2022},
month = jan,
abstract = {It is well known that Drug Design is often a costly process both in terms of time and economic effort. While good Quantitative Structure-Activity Relationship models (QSAR) can help predicting molecular properties without the need to synthesize them, it is still required to come up with new molecules to be tested. This is mostly done in lack of tools to determine which modifications are more promising or which aspects of a molecule are more influential for the final activity/property. Here we present an automatic process which involves Graph Convolutional Network models and input-attribution methods to generate new molecules. We also explore the problems of over-optimization and applicability, recognizing them as two important aspects in the practical use of such automatic tools.},
archiveprefix = {arXiv},
eprint = {2202.05703},
keywords = {q-bio.BM, cs.AI, cs.LG},
primaryclass = {q-bio.BM},
}
Semi-Supervised GCN for learning Molecular Structure-Activity Relationships.
Alessio Ragno, Dylan Savoia, Roberto Capobianco.
ELLIS Machine Learning for Molecules workshop (ML4Molecules).
Paper   BibTeX  
        @Article{Ragno2022,
author = {Alessio Ragno and Dylan Savoia and Roberto Capobianco},
journal = {ELLIS Machine Learning for Molecules workshop (ML4Molecules) 2021},
title = {Semi-Supervised GCN for learning Molecular Structure-Activity Relationships},
year = {2022},
month = jan,
abstract = {Since the introduction of artificial intelligence in medicinal chemistry, the necessity has emerged to analyse how molecular property variation is modulated by either single atoms or chemical groups. In this paper, we propose to train graph-to-graph neural network using semi-supervised learning for attributing structure-property relationships. As initial case studies we apply the method to solubility and molecular acidity while checking its consistency in comparison with known experimental chemical data. As final goal, our approach could represent a valuable tool to deal with problems such as activity cliffs, lead optimization and de-novo drug design.},
archiveprefix = {arXiv},
eprint = {2202.05704},
keywords = {q-bio.BM, cs.AI, cs.LG},
primaryclass = {q-bio.BM},
}
Exploration-Intensive Distractors: Two Environment Proposals and a Benchmarking.
Jim Martin Catacora Ocaña, Roberto Capobianco and Daniele Nardi.
The 20th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2021).
Paper   BibTeX  
        @InProceedings{Ocana2021,
author={Ocana, Jim Martin Catacora and Capobianco, Roberto and Nardi, Daniele},
editor={Bandini, Stefania and Gasparini, Francesca and Mascardi, Viviana and Palmonari, Matteo and Vizzari, Giuseppe},
title={Exploration-Intensive Distractors: Two Environment Proposals and a Benchmarking},
booktitle={AIxIA 2021 -- Advances in Artificial Intelligence},
year={2022},
publisher={Springer International Publishing},
address={Cham},
pages={413--428},
isbn={978-3-031-08421-8},
}
Tafl-ES: Exploring Evolution Strategies for Asymmetrical Board Games.
Roberto Gallotta and Roberto Capobianco.
The 20th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2021).
Paper   BibTeX  
        @InProceedings{Gallotta2021,
author={Gallotta, Roberto and Capobianco, Roberto},
editor={Bandini, Stefania and Gasparini, Francesca and Mascardi, Viviana and Palmonari, Matteo and Vizzari, Giuseppe},
title={Tafl-ES: Exploring Evolution Strategies for Asymmetrical Board Games},
booktitle={AIxIA 2021 -- Advances in Artificial Intelligence},
year={2022},
publisher={Springer International Publishing},
address={Cham},
pages={46--58}, isbn={978-3-031-08421-8},
}
Detection Accuracy for Evaluating Compositional Explanations of Units.
Sayo M. Makinwa, Biagio La Rosa and Roberto Capobianco.
The 20th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2021).
Paper   Code   BibTeX  
        @InProceedings{Makinwa2021,
author={Makinwa, Sayo M. and La Rosa, Biagio and Capobianco, Roberto},
editor={Bandini, Stefania and Gasparini, Francesca and Mascardi, Viviana and Palmonari, Matteo and Vizzari, Giuseppe},
title={Detection Accuracy for Evaluating Compositional Explanations of Units},
booktitle={AIxIA 2021 -- Advances in Artificial Intelligence},
year={2022},
publisher={Springer International Publishing},
address={Cham},
pages={550--563},
isbn={978-3-031-08421-8},
}
A Discussion about Explainable Inference on Sequential Data via Memory-Tracking.
Biagio La Rosa, Roberto Capobianco and Daniele Nardi.
The 20th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2021).
Paper   BibTeX  
        @inproceedings{LaRosa2021,
title = {A Discussion about Explainable Inference on Sequential Data via Memory-Tracking},
author = {La Rosa, Biagio and Capobianco, Roberto and Nardi, Daniele}, booktitle = {AIxIA 2021 Discussion Papers},
publisher = {CEUR Workshop Proceedings},
volume = {3078},
pages = {33-44},
year = {2021},
url = {http://ceur-ws.org/Vol-3078/paper-24.pdf}, }
Agent-Based Markov Modeling for Improved COVID-19 Mitigation Policies.
Roberto Capobianco, Varun Kompella, James Ault, Guni Sharon, Stacy Jong, Spencer Fox, Lauren Meyers, Peter R. Wurman and Peter Stone.
Journal of Artificial Intelligence Research (JAIR).
Paper   BibTeX  
        @inproceedings{capobianco2021covid,
title={Agent-Based {M}arkov Modeling for Improved {COVID}-19 Mitigation Policies},
author={Roberto Capobianco and Varun Kompella and James Ault and Guni Sharon and Stacy Jong and Spencer Fox and Lauren Meyers and Peter R. Wurman and Peter Stone},
month = {August},
year={2021},
pages = {953--992},
Journal = {Journal of Artificial Intelligence Research (JAIR)},
Volume = {71},
Publisher = {Association for the Advancement of Artificial Intelligence}
}
Learning Transferable Policies for Autonomous Planetary Landing via Deep Reinforcement Learning.
Giulia Ciabatti, Roberto Capobianco, Shreyansh Daftry.
Ascend, AIAA.
Paper   BibTeX  
        @InProceedings{Ciabatti2021, author    = {Giulia Ciabatti and Shreyansh Daftry and Roberto Capobianco}, booktitle = {{ASCEND} 2021}, title     = {Learning Transferable Policies for Autonomous Planetary Landing via Deep Reinforcement Learning}, year      = {2021}, month     = {nov}, publisher = {American Institute of Aeronautics and Astronautics}, doi       = {10.2514/6.2021-4006}, }
        
Autonomous Planetary Landing via Deep Reinforcement Learning and Transfer Learning.
Giulia Ciabatti, Shreyansh Daftry and Roberto Capobianco.
AI4Space Workshop (CVPR 2021).
Paper   BibTeX  
        @InProceedings{Ciabatti_2021_CVPR,
author = {Ciabatti, Giulia and Daftry, Shreyansh and Capobianco, Roberto},
title = {Autonomous Planetary Landing via Deep Reinforcement Learning and Transfer Learning},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2021},
pages = {2031-2038} }
Multiagent Epidemiologic Inference through Realtime Contact Tracing.
Guni Sharon, James Ault, Peter Stone, Varun Kompella and Roberto Capobianco.
Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021).
Paper   BibTeX  
        @inproceedings{sharon2021covid,
title={Multiagent Epidemiologic Inference through Realtime Contact Tracing},
author={Sharon, Guni and Ault, James and Stone, Peter and Kompella, Varun and Capobianco, Roberto},
booktitle={Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS 2021)},
location = {London, UK},
month = {May},
year={2021},
organization={International Foundation for Autonomous Agents and Multiagent Systems}
}
2020
LoOP: Iterative learning for optimistic planning on robots.
Francesco Riccio, Roberto Capobianco and Daniele Nardi.
Robotics and Autonomous Systems.
Paper   BibTeX  
        @article{RICCIO2021103693,
title = {LoOP: Iterative learning for optimistic planning on robots},
journal = {Robotics and Autonomous Systems},
abstract = {Efficient robotic behaviors require robustness and adaptation to dynamic changes of the environment, whose characteristics rapidly vary during robot operation. To generate effective robot action policies, planning and learning techniques have shown the most promising results. However, if considered individually, they present different limitations. Planning techniques lack generalization among similar states and require experts to define behavioral routines at different levels of abstraction. Conversely, learning methods usually require a considerable number of training samples and iterations of the algorithm. To overcome these issues, and to efficiently generate robot behaviors, we introduce LoOP, an iterative learning algorithm for optimistic planning that combines state-of-the-art planning and learning techniques to generate action policies. The main contribution of LoOP is the combination of Monte-Carlo Search Planning and Q-learning, which enables focused exploration during policy refinement in different robotic applications. We demonstrate the robustness and flexibility of LoOP in various domains and multiple robotic platforms, by validating the proposed approach with an extensive experimental evaluation.}
volume = {136},
pages = {103693},
year = {2021},
issn = {0921-8890},
doi = {https://doi.org/10.1016/j.robot.2020.103693},
url = {http://www.sciencedirect.com/science/article/pii/S0921889020305339},
author = {Francesco Riccio and Roberto Capobianco and Daniele Nardi},
keywords = {Autonomous planning and learning, Monte-Carlo planning, Q-learning, Deep robot reinforcement learning},
}
Reinforcement Learning for Optimization of COVID-19 Mitigation policies.
Varun Kompella, Roberto Capobianco, Stacy Jong, Jonathan Browne, Spencer Fox, Lauren Meyers, Peter Wurman and Peter Stone.
arXiv preprint.
Paper   Code   BibTeX  
        @misc{kompella2020reinforcement,
title={Reinforcement Learning for Optimization of COVID-19 Mitigation policies},
author={Varun Kompella and Roberto Capobianco and Stacy Jong and Jonathan Browne and Spencer Fox and Lauren Meyers and Peter Wurman and Peter Stone},
year={2020},
eprint={2010.10560},
archivePrefix={arXiv},
primaryClass={cs.LG} }
GUESs: Generative modeling of Unknown Environments and Spatial Abstraction for Robots.
Francesco Riccio, Roberto Capobianco and Daniele Nardi.
Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems.
Paper   BibTeX  
        @inproceedings{10.5555/3398761.3399047,
author = {Riccio, Francesco and Capobianco, Roberto and Nardi, Daniele},
title = {GUESs: Generative Modeling of Unknown Environments and Spatial Abstraction for Robots},
year = {2020},
isbn = {9781450375184},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
address = {Richland, SC},
abstract = {Representing unknown and missing knowledge about the environment is fundamental to leverage robot behavior and improve its performance in completing a task. However, reconstructing spatial knowledge beyond the sensory horizon of the robot is an extremely challenging task. Existing approaches assume that the environment static and features repetitive patterns (e.g. rectangular rooms) or that it can be all generalized with pre-trained models. Our goal is to remove such assumptions and to introduce a novel methodology that allows the robot to represent unknown spatial knowledge in dynamic and unstructured environments. To this end, we exploit generative learning to (1) learn a distribution of spatial landmarks observed during the robot mission and to (2) generate missing information in real-time. The proposed approach aims at supporting planning and decision-making processes needed for robot behaviors. In this paper, we describe architecture modeling the proposed approach and a first validation on a mobile platform.}, booktitle = {Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems},
pages = {1978–1980},
numpages = {3},
keywords = {generative learning, knowledge representation, robot learning},
location = {Auckland, New Zealand},
series = {AAMAS '20} }
Explainable Inference on Sequential Data via Memory-Tracking.
Biagio La Rosa, Roberto Capobianco and Daniele Nardi.
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20).
Paper   Code   BibTeX   Blog Post
        @inproceedings{LaRosa20,
title = {Explainable Inference on Sequential Data via Memory-Tracking},
author = {La Rosa, Biagio and Capobianco, Roberto and Nardi, Daniele},
booktitle = {Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
pages = {2006--2013},
year = {2020},
month = {7},
doi = {10.24963/ijcai.2020/278},
url = {https://doi.org/10.24963/ijcai.2020/278},
}