2 Search Results for "Iocchi, Luca"

Document
DOI: 10.4230/DagMan.10.1.1
Current and Future Challenges in Knowledge Representation and Reasoning (Dagstuhl Perspectives Workshop 22282)

Authors: James P. Delgrande, Birte Glimm, Thomas Meyer, Miroslaw Truszczynski, and Frank Wolter

Published in: Dagstuhl Manifestos, Volume 10, Issue 1 (2024)

Abstract
Knowledge Representation and Reasoning is a central, longstanding, and active area of Artificial Intelligence. Over the years it has evolved significantly; more recently it has been challenged and complemented by research in areas such as machine learning and reasoning under uncertainty. In July 2022,sser a Dagstuhl Perspectives workshop was held on Knowledge Representation and Reasoning. The goal of the workshop was to describe the state of the art in the field, including its relation with other areas, its shortcomings and strengths, together with recommendations for future progress. We developed this manifesto based on the presentations, panels, working groups, and discussions that took place at the Dagstuhl Workshop. It is a declaration of our views on Knowledge Representation: its origins, goals, milestones, and current foci; its relation to other disciplines, especially to Artificial Intelligence; and on its challenges, along with key priorities for the next decade.
Cite as

James P. Delgrande, Birte Glimm, Thomas Meyer, Miroslaw Truszczynski, and Frank Wolter. Current and Future Challenges in Knowledge Representation and Reasoning (Dagstuhl Perspectives Workshop 22282). In Dagstuhl Manifestos, Volume 10, Issue 1, pp. 1-61, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@Article{delgrande_et_al:DagMan.10.1.1,
  author =	{Delgrande, James P. and Glimm, Birte and Meyer, Thomas and Truszczynski, Miroslaw and Wolter, Frank},
  title =	{{Current and Future Challenges in Knowledge Representation and Reasoning (Dagstuhl Perspectives Workshop 22282)}},
  pages =	{1--61},
  journal =	{Dagstuhl Manifestos},
  ISSN =	{2193-2433},
  year =	{2024},
  volume =	{10},
  number =	{1},
  editor =	{Delgrande, James P. and Glimm, Birte and Meyer, Thomas and Truszczynski, Miroslaw and Wolter, Frank},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagMan.10.1.1},
  URN =		{urn:nbn:de:0030-drops-201403},
  doi =		{10.4230/DagMan.10.1.1},
  annote =	{Keywords: Knowledge representation and reasoning, Applications of logics, Declarative representations, Formal logic}
}
Document
DOI: 10.4230/DagSemProc.10081.10
Improving the Performance of Complex Agent Plans Through Reinforcement Learning

Authors: Matteo Leonetti and Luca Iocchi

Published in: Dagstuhl Seminar Proceedings, Volume 10081, Cognitive Robotics (2010)

Abstract
Agent programming in complex, partially observable, and stochastic domains usually requires a great deal of understanding of both the domain and the task in order to provide the agent with the knowledge necessary to act effectively. While symbolic methods allow the designer to specify declarative knowledge about the domain, the resulting plan can be brittle since it is difficult to supply a symbolic model that is accurate enough to foresee all possible events in complex environments, especially in the case of partial observability. Reinforcement Learning (RL) techniques, on the other hand, can learn a policy and make use of a learned model, but it is difficult to reduce and shape the scope of the learning algorithm by exploiting a priori information. We propose a methodology for writing complex agent programs that can be effectively improved through experience.We show how to derive a stochastic process from a partial specification of the plan, so that the latter’s perfomance can be improved solving a RL problem much smaller than classical RL formulations. Finally, we demonstrate our approach in the context of Keepaway Soccer, a common RL benchmark based on a RoboCup Soccer 2D simulator.
Cite as

Matteo Leonetti and Luca Iocchi. Improving the Performance of Complex Agent Plans Through Reinforcement Learning. In Cognitive Robotics. Dagstuhl Seminar Proceedings, Volume 10081, pp. 1-17, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2010)

Copy BibTex To Clipboard

@InProceedings{leonetti_et_al:DagSemProc.10081.10,
  author =	{Leonetti, Matteo and Iocchi, Luca},
  title =	{{Improving the Performance of Complex Agent Plans Through Reinforcement Learning}},
  booktitle =	{Cognitive Robotics},
  pages =	{1--17},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2010},
  volume =	{10081},
  editor =	{Gerhard Lakemeyer and Hector J. Levesque and Fiora Pirri},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.10081.10},
  URN =		{urn:nbn:de:0030-drops-26347},
  doi =		{10.4230/DagSemProc.10081.10},
  annote =	{Keywords: Agent programming, planning, reinforcement learning, semi non-Markov decision process}
}
  • Refine by Author
  • 1 Delgrande, James P.
  • 1 Glimm, Birte
  • 1 Iocchi, Luca
  • 1 Leonetti, Matteo
  • 1 Meyer, Thomas
  • Show More...

  • Refine by Classification
  • 1 Computing methodologies → Artificial intelligence
  • 1 Computing methodologies → Knowledge representation and reasoning
  • 1 Information systems → Information integration
  • 1 Theory of computation → Complexity theory and logic
  • 1 Theory of computation → Logic
  • Show More...

  • Refine by Keyword
  • 1 Agent programming
  • 1 Applications of logics
  • 1 Declarative representations
  • 1 Formal logic
  • 1 Knowledge representation and reasoning
  • Show More...

  • Refine by Type
  • 2 document

  • Refine by Publication Year
  • 1 2010
  • 1 2024

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact