Publications

Copyright Notice: PDFs are provided for personal use and scholarly communication. Copyright remains with the authors or publishers. Please cite the published version and follow the publisher’s terms for reuse.

book Books chapter Book Chapters article Journal Articles Conference Proceedings other Other publications

2026

[c] A. Trapasso, L. Iocchi, and F. Patrizi, “Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes,” in Proceedings of the 35th International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2026), Bremen, Germany, 2026. [Bibtex] [URL]

@inproceedings{TrapassoQRMAX,
  author = {Trapasso, Alessandro and Iocchi, Luca and Patrizi, Fabio},
  title = {Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes},
  year = {2026},
  month = aug,
  address = {Bremen, Germany},
  booktitle = {Proceedings of the 35th International Joint Conference on Artificial Intelligence ({IJCAI-ECAI} 2026)},
  note = {no pdf},
  url = {https://arxiv.org/abs/2512.14617}
}

2025

[c] A. Trapasso and A. Jonsson, “Concurrent Multiagent Reinforcement Learning with Reward Machines,” in Proceedings of the 28th European Conference on Artificial Intelligence (ECAI 2025), Bologna, Italy, 2025, vol. 413. [Bibtex] [PDF] [URL]

@inproceedings{TrapassoJonsson2025Concurrent,
  author = {Trapasso, Alessandro and Jonsson, Anders},
  title = {Concurrent Multiagent Reinforcement Learning with Reward Machines},
  booktitle = {Proceedings of the 28th European Conference on Artificial Intelligence (ECAI 2025)},
  year = {2025},
  month = oct,
  address = {Bologna, Italy},
  series = {Frontiers in Artificial Intelligence and Applications},
  volume = {413},
  publisher = {IOS Press},
  editor = {Lynce, I. and Murano, N. and Vallati, M. and Villata, S. and Chesani, F. and Milano, M. and Omicini, A. and Dastani, M.},
  doi = {10.3233/FAIA251253},
  isbn = {978-1-64368-631-8},
  url = {https://ebooks.iospress.nl/volumearticle/76189?_gl=1*atadje*_up*MQ..*_ga*MzE4MzAxOTMzLjE3NjEzMjk0OTM.*_ga_6N3Q0141SM*czE3NjEzMjk0OTIkbzEkZzEkdDE3NjEzMjk1MDIkajUwJGwwJGgw}
}

[PhD Thesis] A. Trapasso, “Integrating Multi-Agent Planning and Reinforcement Learning through Reward and Exploration Machines,” Sapienza University of Rome, DIAG, 2025. [Bibtex] [URL]

@phdthesis{TrapassoPhD2025,
  author = {Trapasso, Alessandro},
  title = {Integrating Multi-Agent Planning and Reinforcement Learning through Reward and Exploration Machines},
  year = {2025},
  month = oct,
  school = {Sapienza University of Rome, DIAG},
  url = {https://iris.uniroma1.it/handle/11573/1748942},
  note = {no pdf}
}

[j] A. Micheli et al., “Unified Planning: Modeling, manipulating and solving AI planning problems in Python,” SoftwareX, vol. 29, p. 102012, 2025. [Bibtex] [URL]

@article{MICHELI2025102012trapasso,
  title = {Unified Planning: Modeling, manipulating and solving AI planning problems in Python},
  journal = {SoftwareX},
  volume = {29},
  pages = {102012},
  year = {2025},
  issn = {2352-7110},
  doi = {https://doi.org/10.1016/j.softx.2024.102012},
  url = {https://www.sciencedirect.com/science/article/pii/S2352711024003820},
  author = {Micheli, Andrea and Bit-Monnot, Arthur and Röger, Gabriele and Scala, Enrico and Valentini, Alessandro and Framba, Luca and Rovetta, Alberto and Trapasso, Alessandro and Bonassi, Luigi and Gerevini, Alfonso Emilio and Iocchi, Luca and Ingrand, Felix and Köckemann, Uwe and Patrizi, Fabio and Saetti, Alessandro and Serina, Ivan and Stock, Sebastian},
  keywords = {Automated planning and scheduling, Python library, Interoperability},
  note = {no pdf}
}

[c] F. Frattolillo et al., “Discrete Abstraction for Multi-UAV applications with Sparse Rewards using Deep Reinforcement Learning,” in 19th International Conference on Intelligent Autonomous Systems (IAS), 2025. [Bibtex]

@inproceedings{frattolillo2025iastrapasso,
  author = {Frattolillo, Francesco and Maiorana, Flavio and Trapasso, Alessandro and Cadoli, Andrea and Vincelli, Francesco and Vinogradov, Evgenii and Simonjan, Jennifer and Raut, Prasanna and Patrizi, Fabio and Iocchi, Luca},
  title = {Discrete Abstraction for Multi-UAV applications with Sparse Rewards using Deep Reinforcement Learning},
  booktitle = {19th International Conference on Intelligent Autonomous Systems (IAS)},
  year = {2025},
  note = {no pdf}
}

2024

[c] A. Trapasso, M. Bavaro, F. Amigoni, L. Iocchi, and F. Patrizi, “Towards Multi-Agent Model-Based Reinforcement Learning in Discrete Non-Markovian Reward Decision Processes,” in AAPEI ’24: 1st International Workshop on Adjustable Autonomy and Physical Embodied Intelligence, 2024. [Bibtex]

@inproceedings{TrapassoMAQRMAX,
  author = {Trapasso, Alessandro and Bavaro, Marcello and Amigoni, Francesco and Iocchi, Luca and Patrizi, Fabio},
  title = {Towards Multi-Agent Model-Based Reinforcement Learning in Discrete Non-Markovian Reward Decision Processes},
  year = {2024},
  booktitle = {AAPEI ’24: 1st International Workshop on Adjustable Autonomy and Physical Embodied Intelligence},
  note = {no pdf}
}

2023

[c] A. Trapasso, S. Santilli, L. Iocchi, and F. Patrizi, “A Formalization of Multi-Agent Planning with Explicit Agent Representation,” in Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing, New York, NY, USA, 2023, pp. 816–823. [Bibtex] [PDF] [URL]

@inproceedings{trapasso2023,
  author = {Trapasso, Alessandro and Santilli, Sofia and Iocchi, Luca and Patrizi, Fabio},
  title = {A Formalization of Multi-Agent Planning with Explicit Agent Representation},
  year = {2023},
  isbn = {9781450395175},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3555776.3577753},
  doi = {10.1145/3555776.3577753},
  booktitle = {Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing},
  pages = {816--823},
  numpages = {8},
  keywords = {MA-PDDL, multi-agent planning},
  location = {Tallinn, Estonia},
  series = {SAC '23}
}

[c] S. Santilli, A. Trapasso, L. Iocchi, and F. Patrizi, “A novel algorithm for parallelizing actions of a sequential plan,” in 33rd International Conference on Automated Planning and Scheduling (ICAPS 2023) PlanRob Workshop, 2023. [Bibtex] [PDF] [URL]

@inproceedings{planrob2023,
  title = {A novel algorithm for parallelizing actions of a sequential plan},
  author = {Santilli, Sofia and Trapasso, Alessandro and Iocchi, Luca and Patrizi, Fabio},
  booktitle = {33rd International Conference on Automated Planning and Scheduling (ICAPS 2023) PlanRob Workshop},
  url_website = {https://icaps23.icaps-conference.org/},
  url = {https://icaps23.icaps-conference.org/program/workshops/planrob/PlanRob-23_paper_11.pdf},
  year = {2023}
}

2022

[c] N. Brandizzi, D. Brunori, A. Trapasso, F. Frattolillo, and L. Iocchi, “Mixed Human-UAV Reinforcement Learning: Literature Review and Open Challenges,” in The International Conference on Cognitive Aircraft Systems (ICCAS), 2022. [Bibtex] [PDF] [URL]

@inproceedings{iccas2022bbtfi,
  author = {Brandizzi, Nicolo' and Brunori, Damiano and Trapasso, Alessandro and Frattolillo, Francesco and Iocchi, Luca},
  booktitle = {The International Conference on Cognitive Aircraft Systems ({ICCAS})},
  title = {Mixed Human-{UAV} Reinforcement Learning: Literature Review and Open Challenges},
  year = {2022},
  url = {https://events.isae-supaero.fr/event/14/contributions/367/attachments/32/69/Extended_Abstract_ICCAS_2022.pdf}
}

[c] A. Micheli et al., “Unified Planning: A Python Library Making Planning Technology Accessible.,” in In System Demonstrations at the 32nd International Conference on Automated Planning and Scheduling (ICAPS 2022). 2022., 2022. [Bibtex] [URL]

@inproceedings{icaps2022demo,
  title = {Unified Planning: A Python Library Making Planning Technology Accessible.},
  author = {Micheli, Andrea and Arnold, Alexandre and Bit-Monnot, Arthur and Bonassi, Luigi and Framba, Luca and Emilio Gerevini, Alfonso and Hastham Sathiya Satchi, Selvakumar and Helmert, Malte and Ingrand, Felix and Iocchi, Luca and Kockemann, Uwe and Lima, Oscar and Patrizi, Fabio and Pecora, Federico and Poveda, Guillaume and Röger, Gabriele and Saetti, Alessandro and Saffiotti, Alessandro and Scala, Enrico and Serina, Ivan and Stock, Sebastian and Teichteil-Koenigsbuch, Florent and Trapasso, Alessandro and Traverso, Paolo and Valentini, Alessandro},
  booktitle = {In System Demonstrations at the 32nd International Conference on Automated Planning and Scheduling (ICAPS 2022). 2022.},
  url_website = {http://icaps22.icaps-conference.org/},
  url = {https://ai.dmi.unibas.ch/papers/micheli-et-al-icaps2022demo.pdf},
  year = {2022},
  note = {no pdf}
}