Publications
2022
Hayes, Conor F.; Radulescu, Roxana; Bargiacchi, Eugenio; Källström, Johan; Macfarlane, Matthew; Reymond, Mathieu; Verstraeten, Timothy; Zintgraf, Luisa M.; Dazeley, Richard; Heintz, Fredrik; Howley, Enda; Irissappane, Athirai A.; Mannion, Patrick; Nowé, Ann; Ramos, Gabriel Oliveira; Restelli, Marcello; Vamplew, Peter; Roijers, Diederik M.
A practical guide to multi-objective reinforcement learning and planning Journal Article
In: Auton. Agents Multi Agent Syst., vol. 36, no. 1, pp. 26, 2022.
@article{DBLP:journals/aamas/HayesRBKMRVZDHH22,
title = {A practical guide to multi-objective reinforcement learning and planning},
author = {Conor F. Hayes and Roxana Radulescu and Eugenio Bargiacchi and Johan Källström and Matthew Macfarlane and Mathieu Reymond and Timothy Verstraeten and Luisa M. Zintgraf and Richard Dazeley and Fredrik Heintz and Enda Howley and Athirai A. Irissappane and Patrick Mannion and Ann Nowé and Gabriel Oliveira Ramos and Marcello Restelli and Peter Vamplew and Diederik M. Roijers},
url = {https://doi.org/10.1007/s10458-022-09552-y},
doi = {10.1007/s10458-022-09552-y},
year = {2022},
date = {2022-01-01},
journal = {Auton. Agents Multi Agent Syst.},
volume = {36},
number = {1},
pages = {26},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Nuara, Alessandro; Trovò, Francesco; Gatti, Nicola; Restelli, Marcello
Online joint bid/daily budget optimization of Internet advertising campaigns Journal Article
In: Artif. Intell., vol. 305, pp. 103663, 2022.
@article{DBLP:journals/ai/NuaraTGR22,
title = {Online joint bid/daily budget optimization of Internet advertising
campaigns},
author = {Alessandro Nuara and Francesco Trovò and Nicola Gatti and Marcello Restelli},
url = {https://doi.org/10.1016/j.artint.2022.103663},
doi = {10.1016/j.artint.2022.103663},
year = {2022},
date = {2022-01-01},
journal = {Artif. Intell.},
volume = {305},
pages = {103663},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mutti, Mirco; Col, Stefano Del; Restelli, Marcello
Reward-Free Policy Space Compression for Reinforcement Learning Proceedings Article
In: Camps-Valls, Gustau; Ruiz, Francisco J. R.; Valera, Isabel (Ed.): International Conference on Artificial Intelligence and Statistics, AISTATS 2022, 28-30 March 2022, Virtual Event, pp. 3187–3203, PMLR, 2022.
@inproceedings{DBLP:conf/aistats/MuttiCR22,
title = {Reward-Free Policy Space Compression for Reinforcement Learning},
author = {Mirco Mutti and Stefano Del Col and Marcello Restelli},
editor = {Gustau Camps-Valls and Francisco J. R. Ruiz and Isabel Valera},
url = {https://proceedings.mlr.press/v151/mutti22a.html},
year = {2022},
date = {2022-01-01},
booktitle = {International Conference on Artificial Intelligence and Statistics,
AISTATS 2022, 28-30 March 2022, Virtual Event},
volume = {151},
pages = {3187--3203},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Eldowa, Khaled; Bisi, Lorenzo; Restelli, Marcello
Finite Sample Analysis of Mean-Volatility Actor-Critic for Risk-Averse Reinforcement Learning Proceedings Article
In: Camps-Valls, Gustau; Ruiz, Francisco J. R.; Valera, Isabel (Ed.): International Conference on Artificial Intelligence and Statistics, AISTATS 2022, 28-30 March 2022, Virtual Event, pp. 10028–10066, PMLR, 2022.
@inproceedings{DBLP:conf/aistats/EldowaBR22,
title = {Finite Sample Analysis of Mean-Volatility Actor-Critic for Risk-Averse
Reinforcement Learning},
author = {Khaled Eldowa and Lorenzo Bisi and Marcello Restelli},
editor = {Gustau Camps-Valls and Francisco J. R. Ruiz and Isabel Valera},
url = {https://proceedings.mlr.press/v151/eldowa22a.html},
year = {2022},
date = {2022-01-01},
booktitle = {International Conference on Artificial Intelligence and Statistics,
AISTATS 2022, 28-30 March 2022, Virtual Event},
volume = {151},
pages = {10028--10066},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Mutti, Mirco; Santi, Riccardo De; Bartolomeis, Piersilvio De; Restelli, Marcello
Challenging Common Assumptions in Convex Reinforcement Learning Journal Article
In: CoRR, vol. abs/2202.01511, 2022.
@article{DBLP:journals/corr/abs-2202-01511,
title = {Challenging Common Assumptions in Convex Reinforcement Learning},
author = {Mirco Mutti and Riccardo De Santi and Piersilvio De Bartolomeis and Marcello Restelli},
url = {https://arxiv.org/abs/2202.01511},
year = {2022},
date = {2022-01-01},
journal = {CoRR},
volume = {abs/2202.01511},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mutti, Mirco; Santi, Riccardo De; Restelli, Marcello
The Importance of Non-Markovianity in Maximum State Entropy Exploration Journal Article
In: CoRR, vol. abs/2202.03060, 2022.
@article{DBLP:journals/corr/abs-2202-03060,
title = {The Importance of Non-Markovianity in Maximum State Entropy Exploration},
author = {Mirco Mutti and Riccardo De Santi and Marcello Restelli},
url = {https://arxiv.org/abs/2202.03060},
year = {2022},
date = {2022-01-01},
journal = {CoRR},
volume = {abs/2202.03060},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mutti, Mirco; Santi, Riccardo De; Rossi, Emanuele; Calderón, Juan Felipe; Bronstein, Michael M.; Restelli, Marcello
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization Journal Article
In: CoRR, vol. abs/2202.06545, 2022.
@article{DBLP:journals/corr/abs-2202-06545,
title = {Provably Efficient Causal Model-Based Reinforcement Learning for Systematic
Generalization},
author = {Mirco Mutti and Riccardo De Santi and Emanuele Rossi and Juan Felipe Calderón and Michael M. Bronstein and Marcello Restelli},
url = {https://arxiv.org/abs/2202.06545},
year = {2022},
date = {2022-01-01},
journal = {CoRR},
volume = {abs/2202.06545},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mutti, Mirco; Col, Stefano Del; Restelli, Marcello
Reward-Free Policy Space Compression for Reinforcement Learning Journal Article
In: CoRR, vol. abs/2202.11079, 2022.
@article{DBLP:journals/corr/abs-2202-11079,
title = {Reward-Free Policy Space Compression for Reinforcement Learning},
author = {Mirco Mutti and Stefano Del Col and Marcello Restelli},
url = {https://arxiv.org/abs/2202.11079},
year = {2022},
date = {2022-01-01},
journal = {CoRR},
volume = {abs/2202.11079},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Liotet, Pierre; Maran, Davide; Bisi, Lorenzo; Restelli, Marcello
Delayed Reinforcement Learning by Imitation Journal Article
In: CoRR, vol. abs/2205.05569, 2022.
@article{DBLP:journals/corr/abs-2205-05569,
title = {Delayed Reinforcement Learning by Imitation},
author = {Pierre Liotet and Davide Maran and Lorenzo Bisi and Marcello Restelli},
url = {https://doi.org/10.48550/arXiv.2205.05569},
doi = {10.48550/arXiv.2205.05569},
year = {2022},
date = {2022-01-01},
journal = {CoRR},
volume = {abs/2205.05569},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mussi, Marco; Lombarda, Davide; Metelli, Alberto Maria; Trovò, Francesco; Restelli, Marcello
ARLO: A Framework for Automated Reinforcement Learning Journal Article
In: CoRR, vol. abs/2205.10416, 2022.
@article{DBLP:journals/corr/abs-2205-10416,
title = {ARLO: A Framework for Automated Reinforcement Learning},
author = {Marco Mussi and Davide Lombarda and Alberto Maria Metelli and Francesco Trovò and Marcello Restelli},
url = {https://doi.org/10.48550/arXiv.2205.10416},
doi = {10.48550/arXiv.2205.10416},
year = {2022},
date = {2022-01-01},
journal = {CoRR},
volume = {abs/2205.10416},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Riva, Antonio; Bisi, Lorenzo; Liotet, Pierre; Sabbioni, Luca; Vittori, Edoardo; Pinciroli, Marco; Trapletti, Michele; Restelli, Marcello
Addressing Non-Stationarity in FX Trading with Online Model Selection of Offline RL Experts Proceedings Article
In: 3rd ACM International Conference on AI in Finance, pp. 394–402, Association for Computing Machinery, New York, NY, USA, 2022, ISBN: 9781450393768.
Abstract | Links | BibTeX | Tags:
@inproceedings{RivaICAIF2022,
title = {Addressing Non-Stationarity in FX Trading with Online Model Selection of Offline RL Experts},
author = {Antonio Riva and Lorenzo Bisi and Pierre Liotet and Luca Sabbioni and Edoardo Vittori and Marco Pinciroli and Michele Trapletti and Marcello Restelli},
url = {https://doi.org/10.1145/3533271.3561780},
doi = {10.1145/3533271.3561780},
isbn = {9781450393768},
year = {2022},
date = {2022-01-01},
booktitle = {3rd ACM International Conference on AI in Finance},
pages = {394–402},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
series = {ICAIF '22},
abstract = {Reinforcement learning has proven to be successful in obtaining profitable trading policies; however, the effectiveness of such strategies is strongly conditioned to market stationarity. This hypothesis is challenged by the regime switches frequently experienced by practitioners; thus, when many models are available, validation may become a difficult task. We propose to overcome the issue by explicitly modeling the trading task as a non-stationary reinforcement learning problem. Nevertheless, state-of-the-art RL algorithms for this setting usually require task distribution or dynamics to be predictable, an assumption that can hardly be true in the financial framework. In this work, we propose, instead, a method for the dynamic selection of the best RL agent which is only driven by profit performance. Our modular two-layer approach allows choosing the best strategy among a set of RL models through an online-learning algorithm. While we could select any combination of algorithms in principle, our solution employs two state-of-the-art algorithms: Fitted Q-Iteration (FQI) for the RL layer and Optimistic Adapt ML-Prod (OAMP) for the online learning one. The proposed approach is tested on two simulated FX trading tasks, using actual historical data for the AUS/USD and GBP/USD currency pairs.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Bernasconi, Martino; Martino, Stefano; Vittori, Edoardo; Trovò, Francesco; Restelli, Marcello
Dark-Pool Smart Order Routing: A Combinatorial Multi-Armed Bandit Approach Proceedings Article
In: 3rd ACM International Conference on AI in Finance, pp. 352–360, Association for Computing Machinery, New York, NY, USA, 2022, ISBN: 9781450393768.
Abstract | Links | BibTeX | Tags:
@inproceedings{BernasconiICAIF2022,
title = {Dark-Pool Smart Order Routing: A Combinatorial Multi-Armed Bandit Approach},
author = {Martino Bernasconi and Stefano Martino and Edoardo Vittori and Francesco Trovò and Marcello Restelli},
url = {https://doi.org/10.1145/3533271.3561728},
doi = {10.1145/3533271.3561728},
isbn = {9781450393768},
year = {2022},
date = {2022-01-01},
booktitle = {3rd ACM International Conference on AI in Finance},
pages = {352–360},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
series = {ICAIF '22},
abstract = {We study the problem of developing a Smart Order Routing algorithm that learns how to optimize the dollar volume, i.e., the total value of the traded shares, gained from slicing an order across multiple dark pools. Our work is motivated by two distinct issues: (i) the surge in liquidity fragmentation caused by the rising popularity of electronic trading and by the increasing number of trading venues, and (ii) the growth in popularity of dark pools, an exchange venue characterised by a lack of transparency. This paper critically discusses the known dark pool literature and proposes a novel algorithm, namely the DP-CMAB algorithm, that extends existing solutions by allowing the agent to specify the desired limit price when placing orders. Specifically, we frame the problem of dollar volume optimization in a multi-venue setting as a Combinatorial Multi-Armed Bandit (CMAB) problem, representing a generalization of the well-studied MAB framework. Drawing from the rich MAB and CMAB literature, we present multiple strategies that our algorithm may adopt to select the best allocation options. Furthermore, we analyze how exploiting financial domain knowledge improves the agents’ performance. Finally, we evaluate the DP-CMAB performance in an environment built from real market data and show that our algorithm outperforms state-of-the-art solutions.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2021
Metelli, Alberto Maria; Pirotta, Matteo; Calandriello, Daniele; Restelli, Marcello
Safe Policy Iteration: A Monotonically Improving Approximate Policy Iteration Approach Journal Article
In: J. Mach. Learn. Res., vol. 22, pp. 97:1–97:83, 2021.
@article{DBLP:journals/jmlr/MetelliPCR21,
title = {Safe Policy Iteration: A Monotonically Improving Approximate Policy
Iteration Approach},
author = {Alberto Maria Metelli and Matteo Pirotta and Daniele Calandriello and Marcello Restelli},
url = {http://jmlr.org/papers/v22/19-707.html},
year = {2021},
date = {2021-01-01},
journal = {J. Mach. Learn. Res.},
volume = {22},
pages = {97:1--97:83},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
D'Eramo, Carlo; Tateo, Davide; Bonarini, Andrea; Restelli, Marcello; Peters, Jan
MushroomRL: Simplifying Reinforcement Learning Research Journal Article
In: J. Mach. Learn. Res., vol. 22, pp. 131:1–131:5, 2021.
@article{DBLP:journals/jmlr/DEramoTBRP21,
title = {MushroomRL: Simplifying Reinforcement Learning Research},
author = {Carlo D'Eramo and Davide Tateo and Andrea Bonarini and Marcello Restelli and Jan Peters},
url = {http://jmlr.org/papers/v22/18-056.html},
year = {2021},
date = {2021-01-01},
journal = {J. Mach. Learn. Res.},
volume = {22},
pages = {131:1--131:5},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
D'Eramo, Carlo; Cini, Andrea; Nuara, Alessandro; Pirotta, Matteo; Alippi, Cesare; Peters, Jan; Restelli, Marcello
Gaussian Approximation for Bias Reduction in Q-Learning Journal Article
In: J. Mach. Learn. Res., vol. 22, pp. 277:1–277:51, 2021.
@article{DBLP:journals/jmlr/DEramoCNPAPR21,
title = {Gaussian Approximation for Bias Reduction in Q-Learning},
author = {Carlo D'Eramo and Andrea Cini and Alessandro Nuara and Matteo Pirotta and Cesare Alippi and Jan Peters and Marcello Restelli},
url = {http://jmlr.org/papers/v22/20-633.html},
year = {2021},
date = {2021-01-01},
journal = {J. Mach. Learn. Res.},
volume = {22},
pages = {277:1--277:51},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Likmeta, Amarildo; Metelli, Alberto Maria; Ramponi, Giorgia; Tirinzoni, Andrea; Giuliani, Matteo; Restelli, Marcello
Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems Journal Article
In: Mach. Learn., vol. 110, no. 9, pp. 2541–2576, 2021.
@article{DBLP:journals/ml/LikmetaMRTGR21,
title = {Dealing with multiple experts and non-stationarity in inverse reinforcement
learning: an application to real-life problems},
author = {Amarildo Likmeta and Alberto Maria Metelli and Giorgia Ramponi and Andrea Tirinzoni and Matteo Giuliani and Marcello Restelli},
url = {https://doi.org/10.1007/s10994-020-05939-8},
doi = {10.1007/s10994-020-05939-8},
year = {2021},
date = {2021-01-01},
journal = {Mach. Learn.},
volume = {110},
number = {9},
pages = {2541--2576},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Metelli, Alberto Maria; Papini, Matteo; D'Oro, Pierluca; Restelli, Marcello
Policy Optimization as Online Learning with Mediator Feedback Proceedings Article
In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, pp. 8958–8966, AAAI Press, 2021.
@inproceedings{DBLP:conf/aaai/MetelliPDR21,
title = {Policy Optimization as Online Learning with Mediator Feedback},
author = {Alberto Maria Metelli and Matteo Papini and Pierluca D'Oro and Marcello Restelli},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/17083},
year = {2021},
date = {2021-01-01},
booktitle = {Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9,
2021},
pages = {8958--8966},
publisher = {AAAI Press},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Mutti, Mirco; Pratissoli, Lorenzo; Restelli, Marcello
Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate Proceedings Article
In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, pp. 9028–9036, AAAI Press, 2021.
@inproceedings{DBLP:conf/aaai/MuttiPR21,
title = {Task-Agnostic Exploration via Policy Gradient of a Non-Parametric
State Entropy Estimate},
author = {Mirco Mutti and Lorenzo Pratissoli and Marcello Restelli},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/17091},
year = {2021},
date = {2021-01-01},
booktitle = {Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9,
2021},
pages = {9028--9036},
publisher = {AAAI Press},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ramponi, Giorgia; Restelli, Marcello
Newton Optimization on Helmholtz Decomposition for Continuous Games Proceedings Article
In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, pp. 11325–11333, AAAI Press, 2021.
@inproceedings{DBLP:conf/aaai/RamponiR21,
title = {Newton Optimization on Helmholtz Decomposition for Continuous Games},
author = {Giorgia Ramponi and Marcello Restelli},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/17350},
year = {2021},
date = {2021-01-01},
booktitle = {Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9,
2021},
pages = {11325--11333},
publisher = {AAAI Press},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Vittori, Edoardo; Likmeta, Amarildo; Restelli, Marcello
Monte carlo tree search for trading and hedging Proceedings Article
In: Calinescu, Anisoara; Szpruch, Lukasz (Ed.): ICAIF'21: 2nd ACM International Conference on AI in Finance, Virtual Event, November 3 - 5, 2021, pp. 37:1–37:9, ACM, 2021.
@inproceedings{DBLP:conf/icaif/VittoriLR21,
title = {Monte carlo tree search for trading and hedging},
author = {Edoardo Vittori and Amarildo Likmeta and Marcello Restelli},
editor = {Anisoara Calinescu and Lukasz Szpruch},
url = {https://doi.org/10.1145/3490354.3494402},
doi = {10.1145/3490354.3494402},
year = {2021},
date = {2021-01-01},
booktitle = {ICAIF'21: 2nd ACM International Conference on AI in Finance, Virtual
Event, November 3 - 5, 2021},
pages = {37:1--37:9},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Riva, Antonio; Bisi, Lorenzo; Liotet, Pierre; Sabbioni, Luca; Vittori, Edoardo; Pinciroli, Marco; Trapletti, Michele; Restelli, Marcello
Learning FX trading strategies with FQI and persistent actions Proceedings Article
In: Calinescu, Anisoara; Szpruch, Lukasz (Ed.): ICAIF'21: 2nd ACM International Conference on AI in Finance, Virtual Event, November 3 - 5, 2021, pp. 38:1–38:9, ACM, 2021.
@inproceedings{DBLP:conf/icaif/RivaBLSVPTR21,
title = {Learning FX trading strategies with FQI and persistent actions},
author = {Antonio Riva and Lorenzo Bisi and Pierre Liotet and Luca Sabbioni and Edoardo Vittori and Marco Pinciroli and Michele Trapletti and Marcello Restelli},
editor = {Anisoara Calinescu and Lukasz Szpruch},
url = {https://doi.org/10.1145/3490354.3494403},
doi = {10.1145/3490354.3494403},
year = {2021},
date = {2021-01-01},
booktitle = {ICAIF'21: 2nd ACM International Conference on AI in Finance, Virtual
Event, November 3 - 5, 2021},
pages = {38:1--38:9},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Metelli, Alberto Maria; Ramponi, Giorgia; Concetti, Alessandro; Restelli, Marcello
Provably Efficient Learning of Transferable Rewards Proceedings Article
In: Meila, Marina; Zhang, Tong (Ed.): Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, pp. 7665–7676, PMLR, 2021.
@inproceedings{DBLP:conf/icml/MetelliRCR21,
title = {Provably Efficient Learning of Transferable Rewards},
author = {Alberto Maria Metelli and Giorgia Ramponi and Alessandro Concetti and Marcello Restelli},
editor = {Marina Meila and Tong Zhang},
url = {http://proceedings.mlr.press/v139/metelli21a.html},
year = {2021},
date = {2021-01-01},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
ICML 2021, 18-24 July 2021, Virtual Event},
volume = {139},
pages = {7665--7676},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Papini, Matteo; Tirinzoni, Andrea; Restelli, Marcello; Lazaric, Alessandro; Pirotta, Matteo
Leveraging Good Representations in Linear Contextual Bandits Proceedings Article
In: Meila, Marina; Zhang, Tong (Ed.): Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, pp. 8371–8380, PMLR, 2021.
@inproceedings{DBLP:conf/icml/PapiniTRLP21,
title = {Leveraging Good Representations in Linear Contextual Bandits},
author = {Matteo Papini and Andrea Tirinzoni and Marcello Restelli and Alessandro Lazaric and Matteo Pirotta},
editor = {Marina Meila and Tong Zhang},
url = {http://proceedings.mlr.press/v139/papini21a.html},
year = {2021},
date = {2021-01-01},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
ICML 2021, 18-24 July 2021, Virtual Event},
volume = {139},
pages = {8371--8380},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Poiani, Riccardo; Tirinzoni, Andrea; Restelli, Marcello
Meta-Reinforcement Learning by Tracking Task Non-stationarity Proceedings Article
In: Zhou, Zhi-Hua (Ed.): Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Virtual Event / Montreal, Canada, 19-27 August 2021, pp. 2899–2905, ijcai.org, 2021.
@inproceedings{DBLP:conf/ijcai/PoianiTR21,
title = {Meta-Reinforcement Learning by Tracking Task Non-stationarity},
author = {Riccardo Poiani and Andrea Tirinzoni and Marcello Restelli},
editor = {Zhi-Hua Zhou},
url = {https://doi.org/10.24963/ijcai.2021/399},
doi = {10.24963/ijcai.2021/399},
year = {2021},
date = {2021-01-01},
booktitle = {Proceedings of the Thirtieth International Joint Conference on Artificial
Intelligence, IJCAI 2021, Virtual Event / Montreal, Canada, 19-27
August 2021},
pages = {2899--2905},
publisher = {ijcai.org},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Liotet, Pierre; Venneri, Erick; Restelli, Marcello
Learning a Belief Representation for Delayed Reinforcement Learning Proceedings Article
In: International Joint Conference on Neural Networks, IJCNN 2021, Shenzhen, China, July 18-22, 2021, pp. 1–8, IEEE, 2021.
@inproceedings{DBLP:conf/ijcnn/LiotetVR21,
title = {Learning a Belief Representation for Delayed Reinforcement Learning},
author = {Pierre Liotet and Erick Venneri and Marcello Restelli},
url = {https://doi.org/10.1109/IJCNN52387.2021.9534358},
doi = {10.1109/IJCNN52387.2021.9534358},
year = {2021},
date = {2021-01-01},
booktitle = {International Joint Conference on Neural Networks, IJCNN 2021, Shenzhen,
China, July 18-22, 2021},
pages = {1--8},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Metelli, Alberto Maria; Russo, Alessio; Restelli, Marcello
Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning Proceedings Article
In: Ranzato, Marc'Aurelio; Beygelzimer, Alina; Dauphin, Yann N.; Liang, Percy; Vaughan, Jennifer Wortman (Ed.): Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pp. 8119–8132, 2021.
@inproceedings{DBLP:conf/nips/MetelliRR21,
title = {Subgaussian and Differentiable Importance Sampling for Off-Policy
Evaluation and Learning},
author = {Alberto Maria Metelli and Alessio Russo and Marcello Restelli},
editor = {Marc'Aurelio Ranzato and Alina Beygelzimer and Yann N. Dauphin and Percy Liang and Jennifer Wortman Vaughan},
url = {https://proceedings.neurips.cc/paper/2021/hash/4476b929e30dd0c4e8bdbcc82c6ba23a-Abstract.html},
year = {2021},
date = {2021-01-01},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {8119--8132},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Papini, Matteo; Tirinzoni, Andrea; Pacchiano, Aldo; Restelli, Marcello; Lazaric, Alessandro; Pirotta, Matteo
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection Proceedings Article
In: Ranzato, Marc'Aurelio; Beygelzimer, Alina; Dauphin, Yann N.; Liang, Percy; Vaughan, Jennifer Wortman (Ed.): Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pp. 16371–16383, 2021.
@inproceedings{DBLP:conf/nips/PapiniTPRLP21,
title = {Reinforcement Learning in Linear MDPs: Constant Regret and Representation
Selection},
author = {Matteo Papini and Andrea Tirinzoni and Aldo Pacchiano and Marcello Restelli and Alessandro Lazaric and Matteo Pirotta},
editor = {Marc'Aurelio Ranzato and Alina Beygelzimer and Yann N. Dauphin and Percy Liang and Jennifer Wortman Vaughan},
url = {https://proceedings.neurips.cc/paper/2021/hash/8860e834a67da41edd6ffe8a1c58fa55-Abstract.html},
year = {2021},
date = {2021-01-01},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {16371--16383},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ramponi, Giorgia; Metelli, Alberto Maria; Concetti, Alessandro; Restelli, Marcello
Learning in Non-Cooperative Configurable Markov Decision Processes Proceedings Article
In: Ranzato, Marc'Aurelio; Beygelzimer, Alina; Dauphin, Yann N.; Liang, Percy; Vaughan, Jennifer Wortman (Ed.): Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pp. 22808–22821, 2021.
@inproceedings{DBLP:conf/nips/RamponiMCR21,
title = {Learning in Non-Cooperative Configurable Markov Decision Processes},
author = {Giorgia Ramponi and Alberto Maria Metelli and Alessandro Concetti and Marcello Restelli},
editor = {Marc'Aurelio Ranzato and Alina Beygelzimer and Yann N. Dauphin and Percy Liang and Jennifer Wortman Vaughan},
url = {https://proceedings.neurips.cc/paper/2021/hash/c0f52c6624ae1359e105c8a5d8cd956a-Abstract.html},
year = {2021},
date = {2021-01-01},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {22808--22821},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Luca, Martino Bernasconi; Vittori, Edoardo; Trovò, Francesco; Restelli, Marcello
Conservative Online Convex Optimization Proceedings Article
In: Oliver, Nuria; Pérez-Cruz, Fernando; Kramer, Stefan; Read, Jesse; Lozano, José Antonio (Ed.): Machine Learning and Knowledge Discovery in Databases. Research Track - European Conference, ECML PKDD 2021, Bilbao, Spain, September 13-17, 2021, Proceedings, Part I, pp. 19–34, Springer, 2021.
@inproceedings{DBLP:conf/pkdd/LucaVTR21,
title = {Conservative Online Convex Optimization},
author = {Martino Bernasconi Luca and Edoardo Vittori and Francesco Trovò and Marcello Restelli},
editor = {Nuria Oliver and Fernando Pérez-Cruz and Stefan Kramer and Jesse Read and José Antonio Lozano},
url = {https://doi.org/10.1007/978-3-030-86486-6_2},
doi = {10.1007/978-3-030-86486-6_2},
year = {2021},
date = {2021-01-01},
booktitle = {Machine Learning and Knowledge Discovery in Databases. Research Track
- European Conference, ECML PKDD 2021, Bilbao, Spain, September
13-17, 2021, Proceedings, Part I},
volume = {12975},
pages = {19--34},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Re, Gerlando; Chiusano, Fabio; Trovò, Francesco; Carrera, Diego; Boracchi, Giacomo; Restelli, Marcello
Exploiting History Data for Nonstationary Multi-armed Bandit Proceedings Article
In: Oliver, Nuria; Pérez-Cruz, Fernando; Kramer, Stefan; Read, Jesse; Lozano, José Antonio (Ed.): Machine Learning and Knowledge Discovery in Databases. Research Track - European Conference, ECML PKDD 2021, Bilbao, Spain, September 13-17, 2021, Proceedings, Part I, pp. 51–66, Springer, 2021.
@inproceedings{DBLP:conf/pkdd/ReCTCBR21,
title = {Exploiting History Data for Nonstationary Multi-armed Bandit},
author = {Gerlando Re and Fabio Chiusano and Francesco Trovò and Diego Carrera and Giacomo Boracchi and Marcello Restelli},
editor = {Nuria Oliver and Fernando Pérez-Cruz and Stefan Kramer and Jesse Read and José Antonio Lozano},
url = {https://doi.org/10.1007/978-3-030-86486-6_4},
doi = {10.1007/978-3-030-86486-6_4},
year = {2021},
date = {2021-01-01},
booktitle = {Machine Learning and Knowledge Discovery in Databases. Research Track
- European Conference, ECML PKDD 2021, Bilbao, Spain, September
13-17, 2021, Proceedings, Part I},
volume = {12975},
pages = {51--66},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Canonaco, Giuseppe; Soprani, Andrea; Giuliani, Matteo; Castelletti, Andrea; Roveri, Manuel; Restelli, Marcello
Time-variant variational transfer for value functions Proceedings Article
In: Campos, Cassio P.; Maathuis, Marloes H.; Quaeghebeur, Erik (Ed.): Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, UAI 2021, Virtual Event, 27-30 July 2021, pp. 876–886, AUAI Press, 2021.
@inproceedings{DBLP:conf/uai/CanonacoSGCRR21,
title = {Time-variant variational transfer for value functions},
author = {Giuseppe Canonaco and Andrea Soprani and Matteo Giuliani and Andrea Castelletti and Manuel Roveri and Marcello Restelli},
editor = {Cassio P. Campos and Marloes H. Maathuis and Erik Quaeghebeur},
url = {https://proceedings.mlr.press/v161/canonaco21a.html},
year = {2021},
date = {2021-01-01},
booktitle = {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial
Intelligence, UAI 2021, Virtual Event, 27-30 July 2021},
volume = {161},
pages = {876--886},
publisher = {AUAI Press},
series = {Proceedings of Machine Learning Research},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Hayes, Conor F.; Radulescu, Roxana; Bargiacchi, Eugenio; Källström, Johan; Macfarlane, Matthew; Reymond, Mathieu; Verstraeten, Timothy; Zintgraf, Luisa M.; Dazeley, Richard; Heintz, Fredrik; Howley, Enda; Irissappane, Athirai A.; Mannion, Patrick; Nowé, Ann; Ramos, Gabriel Oliveira; Restelli, Marcello; Vamplew, Peter; Roijers, Diederik M.
A Practical Guide to Multi-Objective Reinforcement Learning and Planning Journal Article
In: CoRR, vol. abs/2103.09568, 2021.
@article{DBLP:journals/corr/abs-2103-09568,
title = {A Practical Guide to Multi-Objective Reinforcement Learning and Planning},
author = {Conor F. Hayes and Roxana Radulescu and Eugenio Bargiacchi and Johan Källström and Matthew Macfarlane and Mathieu Reymond and Timothy Verstraeten and Luisa M. Zintgraf and Richard Dazeley and Fredrik Heintz and Enda Howley and Athirai A. Irissappane and Patrick Mannion and Ann Nowé and Gabriel Oliveira Ramos and Marcello Restelli and Peter Vamplew and Diederik M. Roijers},
url = {https://arxiv.org/abs/2103.09568},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2103.09568},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Papini, Matteo; Tirinzoni, Andrea; Restelli, Marcello; Lazaric, Alessandro; Pirotta, Matteo
Leveraging Good Representations in Linear Contextual Bandits Journal Article
In: CoRR, vol. abs/2104.03781, 2021.
@article{DBLP:journals/corr/abs-2104-03781,
title = {Leveraging Good Representations in Linear Contextual Bandits},
author = {Matteo Papini and Andrea Tirinzoni and Marcello Restelli and Alessandro Lazaric and Matteo Pirotta},
url = {https://arxiv.org/abs/2104.03781},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2104.03781},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Poiani, Riccardo; Tirinzoni, Andrea; Restelli, Marcello
Meta-Reinforcement Learning by Tracking Task Non-stationarity Journal Article
In: CoRR, vol. abs/2105.08834, 2021.
@article{DBLP:journals/corr/abs-2105-08834,
title = {Meta-Reinforcement Learning by Tracking Task Non-stationarity},
author = {Riccardo Poiani and Andrea Tirinzoni and Marcello Restelli},
url = {https://arxiv.org/abs/2105.08834},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.08834},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Papini, Matteo; Tirinzoni, Andrea; Pacchiano, Aldo; Restelli, Marcello; Lazaric, Alessandro; Pirotta, Matteo
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection Journal Article
In: CoRR, vol. abs/2110.14798, 2021.
@article{DBLP:journals/corr/abs-2110-14798,
title = {Reinforcement Learning in Linear MDPs: Constant Regret and Representation
Selection},
author = {Matteo Papini and Andrea Tirinzoni and Aldo Pacchiano and Marcello Restelli and Alessandro Lazaric and Matteo Pirotta},
url = {https://arxiv.org/abs/2110.14798},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.14798},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Liotet, Pierre; Vidaich, Francesco; Metelli, Alberto Maria; Restelli, Marcello
Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization Journal Article
In: CoRR, vol. abs/2112.06625, 2021.
@article{DBLP:journals/corr/abs-2112-06625,
title = {Lifelong Hyper-Policy Optimization with Multiple Importance Sampling
Regularization},
author = {Pierre Liotet and Francesco Vidaich and Alberto Maria Metelli and Marcello Restelli},
url = {https://arxiv.org/abs/2112.06625},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2112.06625},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mutti, Mirco; Mancassola, Mattia; Restelli, Marcello
Unsupervised Reinforcement Learning in Multiple Environments Journal Article
In: CoRR, vol. abs/2112.08746, 2021.
@article{DBLP:journals/corr/abs-2112-08746,
title = {Unsupervised Reinforcement Learning in Multiple Environments},
author = {Mirco Mutti and Mattia Mancassola and Marcello Restelli},
url = {https://arxiv.org/abs/2112.08746},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2112.08746},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2020
Metelli, Alberto Maria; Pirotta, Matteo; Restelli, Marcello
On the use of the policy gradient and Hessian in inverse reinforcement learning Journal Article
In: Intelligenza Artificiale, vol. 14, no. 1, pp. 117–150, 2020.
@article{DBLP:journals/ia/MetelliPR20,
title = {On the use of the policy gradient and Hessian in inverse reinforcement
learning},
author = {Alberto Maria Metelli and Matteo Pirotta and Marcello Restelli},
url = {https://doi.org/10.3233/IA-180011},
doi = {10.3233/IA-180011},
year = {2020},
date = {2020-01-01},
journal = {Intelligenza Artificiale},
volume = {14},
number = {1},
pages = {117--150},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Trovò, Francesco; Restelli, Marcello; Gatti, Nicola
Sliding-Window Thompson Sampling for Non-Stationary Settings Journal Article
In: J. Artif. Intell. Res., vol. 68, pp. 311–364, 2020.
@article{DBLP:journals/jair/TrovoRG20,
title = {Sliding-Window Thompson Sampling for Non-Stationary Settings},
author = {Francesco Trovò and Marcello Restelli and Nicola Gatti},
url = {https://doi.org/10.1613/jair.1.11407},
doi = {10.1613/jair.1.11407},
year = {2020},
date = {2020-01-01},
journal = {J. Artif. Intell. Res.},
volume = {68},
pages = {311--364},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Metelli, Alberto Maria; Papini, Matteo; Montali, Nico; Restelli, Marcello
Importance Sampling Techniques for Policy Optimization Journal Article
In: J. Mach. Learn. Res., vol. 21, pp. 141:1–141:75, 2020.
@article{DBLP:journals/jmlr/MetelliPMR20,
title = {Importance Sampling Techniques for Policy Optimization},
author = {Alberto Maria Metelli and Matteo Papini and Nico Montali and Marcello Restelli},
url = {http://jmlr.org/papers/v21/20-124.html},
year = {2020},
date = {2020-01-01},
journal = {J. Mach. Learn. Res.},
volume = {21},
pages = {141:1--141:75},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Likmeta, Amarildo; Metelli, Alberto Maria; Tirinzoni, Andrea; Giol, Riccardo; Restelli, Marcello; Romano, Danilo
Combining reinforcement learning with rule-based controllers for transparent and general decision-making in autonomous driving Journal Article
In: Robotics Auton. Syst., vol. 131, pp. 103568, 2020.
@article{DBLP:journals/ras/LikmetaMTGRR20,
title = {Combining reinforcement learning with rule-based controllers for transparent
and general decision-making in autonomous driving},
author = {Amarildo Likmeta and Alberto Maria Metelli and Andrea Tirinzoni and Riccardo Giol and Marcello Restelli and Danilo Romano},
url = {https://doi.org/10.1016/j.robot.2020.103568},
doi = {10.1016/j.robot.2020.103568},
year = {2020},
date = {2020-01-01},
journal = {Robotics Auton. Syst.},
volume = {131},
pages = {103568},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
D'Oro, Pierluca; Metelli, Alberto Maria; Tirinzoni, Andrea; Papini, Matteo; Restelli, Marcello
Gradient-Aware Model-Based Policy Search Proceedings Article
In: The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020, pp. 3801–3808, AAAI Press, 2020.
@inproceedings{DBLP:conf/aaai/DOroMTPR20,
title = {Gradient-Aware Model-Based Policy Search},
author = {Pierluca D'Oro and Alberto Maria Metelli and Andrea Tirinzoni and Matteo Papini and Marcello Restelli},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/5791},
year = {2020},
date = {2020-01-01},
booktitle = {The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI
2020, The Thirty-Second Innovative Applications of Artificial Intelligence
Conference, IAAI 2020, The Tenth AAAI Symposium on Educational
Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA,
February 7-12, 2020},
pages = {3801--3808},
publisher = {AAAI Press},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Mutti, Mirco; Restelli, Marcello
An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies Proceedings Article
In: The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020, pp. 5232–5239, AAAI Press, 2020.
@inproceedings{DBLP:conf/aaai/MuttiR20,
title = {An Intrinsically-Motivated Approach for Learning Highly Exploring
and Fast Mixing Policies},
author = {Mirco Mutti and Marcello Restelli},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/5968},
year = {2020},
date = {2020-01-01},
booktitle = {The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI
2020, The Thirty-Second Innovative Applications of Artificial Intelligence
Conference, IAAI 2020, The Tenth AAAI Symposium on Educational
Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA,
February 7-12, 2020},
pages = {5232--5239},
publisher = {AAAI Press},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Papini, Matteo; Battistello, Andrea; Restelli, Marcello
Balancing Learning Speed and Stability in Policy Gradient via Adaptive Exploration Proceedings Article
In: Chiappa, Silvia; Calandra, Roberto (Ed.): The 23rd International Conference on Artificial Intelligence and Statistics, AISTATS 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy], pp. 1188–1199, PMLR, 2020.
@inproceedings{DBLP:conf/aistats/PapiniBR20,
title = {Balancing Learning Speed and Stability in Policy Gradient via Adaptive
Exploration},
author = {Matteo Papini and Andrea Battistello and Marcello Restelli},
editor = {Silvia Chiappa and Roberto Calandra},
url = {http://proceedings.mlr.press/v108/papini20a.html},
year = {2020},
date = {2020-01-01},
booktitle = {The 23rd International Conference on Artificial Intelligence and Statistics,
AISTATS 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy]},
volume = {108},
pages = {1188--1199},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ramponi, Giorgia; Likmeta, Amarildo; Metelli, Alberto Maria; Tirinzoni, Andrea; Restelli, Marcello
Truly Batch Model-Free Inverse Reinforcement Learning about Multiple Intentions Proceedings Article
In: Chiappa, Silvia; Calandra, Roberto (Ed.): The 23rd International Conference on Artificial Intelligence and Statistics, AISTATS 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy], pp. 2359–2369, PMLR, 2020.
@inproceedings{DBLP:conf/aistats/RamponiLMTR20,
title = {Truly Batch Model-Free Inverse Reinforcement Learning about Multiple
Intentions},
author = {Giorgia Ramponi and Amarildo Likmeta and Alberto Maria Metelli and Andrea Tirinzoni and Marcello Restelli},
editor = {Silvia Chiappa and Roberto Calandra},
url = {http://proceedings.mlr.press/v108/ramponi20a.html},
year = {2020},
date = {2020-01-01},
booktitle = {The 23rd International Conference on Artificial Intelligence and Statistics,
AISTATS 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy]},
volume = {108},
pages = {2359--2369},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Tirinzoni, Andrea; Lazaric, Alessandro; Restelli, Marcello
A Novel Confidence-Based Algorithm for Structured Bandits Proceedings Article
In: Chiappa, Silvia; Calandra, Roberto (Ed.): The 23rd International Conference on Artificial Intelligence and Statistics, AISTATS 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy], pp. 3175–3185, PMLR, 2020.
@inproceedings{DBLP:conf/aistats/TirinzoniLR20,
title = {A Novel Confidence-Based Algorithm for Structured Bandits},
author = {Andrea Tirinzoni and Alessandro Lazaric and Marcello Restelli},
editor = {Silvia Chiappa and Roberto Calandra},
url = {http://proceedings.mlr.press/v108/tirinzoni20a.html},
year = {2020},
date = {2020-01-01},
booktitle = {The 23rd International Conference on Artificial Intelligence and Statistics,
AISTATS 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy]},
volume = {108},
pages = {3175--3185},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Nuara, Alessandro; Trovò, Francesco; Crippa, Dominic; Gatti, Nicola; Restelli, Marcello
Driving Exploration by Maximum Distribution in Gaussian Process Bandits Proceedings Article
In: Seghrouchni, Amal El Fallah; Sukthankar, Gita; An, Bo; Yorke-Smith, Neil (Ed.): Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS '20, Auckland, New Zealand, May 9-13, 2020, pp. 948–956, International Foundation for Autonomous Agents and Multiagent Systems, 2020.
@inproceedings{DBLP:conf/atal/NuaraTC0R20,
title = {Driving Exploration by Maximum Distribution in Gaussian Process Bandits},
author = {Alessandro Nuara and Francesco Trovò and Dominic Crippa and Nicola Gatti and Marcello Restelli},
editor = {Amal El Fallah Seghrouchni and Gita Sukthankar and Bo An and Neil Yorke-Smith},
url = {https://dl.acm.org/doi/10.5555/3398761.3398872},
doi = {10.5555/3398761.3398872},
year = {2020},
date = {2020-01-01},
booktitle = {Proceedings of the 19th International Conference on Autonomous Agents
and Multiagent Systems, AAMAS '20, Auckland, New Zealand, May 9-13,
2020},
pages = {948--956},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Canonaco, Giuseppe; Restelli, Marcello; Roveri, Manuel
Model-Free Non-Stationarity Detection and Adaptation in Reinforcement Learning Proceedings Article
In: Giacomo, Giuseppe De; Catalá, Alejandro; Dilkina, Bistra; Milano, Michela; Barro, Senén; Bugarín, Alberto; Lang, Jérôme (Ed.): ECAI 2020 - 24th European Conference on Artificial Intelligence, 29 August-8 September 2020, Santiago de Compostela, Spain, August 29 - September 8, 2020 - Including 10th Conference on Prestigious Applications of Artificial Intelligence (PAIS 2020), pp. 1047–1054, IOS Press, 2020.
@inproceedings{DBLP:conf/ecai/CanonacoRR20,
title = {Model-Free Non-Stationarity Detection and Adaptation in Reinforcement
Learning},
author = {Giuseppe Canonaco and Marcello Restelli and Manuel Roveri},
editor = {Giuseppe De Giacomo and Alejandro Catalá and Bistra Dilkina and Michela Milano and Senén Barro and Alberto Bugarín and Jérôme Lang},
url = {https://doi.org/10.3233/FAIA200200},
doi = {10.3233/FAIA200200},
year = {2020},
date = {2020-01-01},
booktitle = {ECAI 2020 - 24th European Conference on Artificial Intelligence,
29 August-8 September 2020, Santiago de Compostela, Spain, August
29 - September 8, 2020 - Including 10th Conference on Prestigious
Applications of Artificial Intelligence (PAIS 2020)},
volume = {325},
pages = {1047--1054},
publisher = {IOS Press},
series = {Frontiers in Artificial Intelligence and Applications},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sabbioni, Luca; Restelli, Marcello; Prampolini, Andrea
Fast direct calibration of interest rate derivatives pricing models Proceedings Article
In: Balch, Tucker (Ed.): ICAIF '20: The First ACM International Conference on AI in Finance, New York, NY, USA, October 15-16, 2020, pp. 6:1–6:8, ACM, 2020.
@inproceedings{DBLP:conf/icaif/SabbioniRP20,
title = {Fast direct calibration of interest rate derivatives pricing models},
author = {Luca Sabbioni and Marcello Restelli and Andrea Prampolini},
editor = {Tucker Balch},
url = {https://doi.org/10.1145/3383455.3422534},
doi = {10.1145/3383455.3422534},
year = {2020},
date = {2020-01-01},
booktitle = {ICAIF '20: The First ACM International Conference on AI in Finance,
New York, NY, USA, October 15-16, 2020},
pages = {6:1--6:8},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Vittori, Edoardo; Luca, Martino Bernasconi; Trovò, Francesco; Restelli, Marcello
Dealing with transaction costs in portfolio optimization: online gradient descent with momentum Proceedings Article
In: Balch, Tucker (Ed.): ICAIF '20: The First ACM International Conference on AI in Finance, New York, NY, USA, October 15-16, 2020, pp. 11:1–11:8, ACM, 2020.
@inproceedings{DBLP:conf/icaif/VittoriLTR20,
title = {Dealing with transaction costs in portfolio optimization: online gradient
descent with momentum},
author = {Edoardo Vittori and Martino Bernasconi Luca and Francesco Trovò and Marcello Restelli},
editor = {Tucker Balch},
url = {https://doi.org/10.1145/3383455.3422531},
doi = {10.1145/3383455.3422531},
year = {2020},
date = {2020-01-01},
booktitle = {ICAIF '20: The First ACM International Conference on AI in Finance,
New York, NY, USA, October 15-16, 2020},
pages = {11:1--11:8},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}