Specializing TEmporal Planning using Reinforcement Learning

Project Information

STEP-RL

Grant agreement ID: 101115870

DOI 10.3030/101115870

EC signature date 18 September 2023

Start date 1 January 2024

End date 31 December 2028

Funded under

• European Research Council (ERC)

Total cost € 1 493 750,00

EU contribution € 1 493 750,00

Coordinated by

FONDAZIONE BRUNO KESSLER
Italy

Objective

"Planning - devising a strategy to achieve a desired objective - is one of the basic forms of intelligence. Temporal planning studies the automated synthesis of strategies when time and temporal constraints matter. Temporal planning is one of the most strategic fields of Artificial Intelligence, with applications in autonomous robotics, logistics, flexible production, and many other fields.

Historically, the research on temporal planning follows a general-purpose framework: a generic engine searches for the strategy by reasoning on the problem statement (i.e. the starting condition and the desired objective), as well as on a formal model of the domain (i.e. the possible actions). Despite substantial progress in the recent years, domain-independent temporal planning still suffers from scalability issues, and fails to deal with real-word problems. The alternative is to devise ad-hoc, domain-specific solutions that, although efficient, are costly to develop, rigid to maintain, and often inapplicable in non-nominal situations.

STEP-RL will study the foundations of a new approach to Temporal Planning, that is domain-independent and efficient at the same time. The idea is to adopt a framework based on Reinforcement Learning, where a domain-independent temporal planner is specialized with respect to the domain at hand. STEP-RL continuously improves its ability to solve temporal planning problems by learning from experience, thus becoming increasingly efficient by means of self-adaptation.

STEP-RL will advance the state of the art in temporal planning beyond the ""efficiency vs flexibility"" dilemma, that I had to personally face in the many industrial projects I worked on."

Fields of science

• natural sciences › computer and information sciences › artificial intelligence › machine learning › reinforcement learning
• engineering and technology › electrical engineering, electronic engineering, information engineering › electronic engineering › robotics › autonomous robots

Keywords

• Automated Planning
• Planning and Scheduling
• Automated Decision-Making

Programme(s)

• HORIZON.1.1 - European Research Council (ERC) Main Programme

Topic(s)

• ERC-2023-STG - ERC STARTING GRANTS

Call for proposal

ERC-2023-STG

Funding Scheme

HORIZON-ERC - HORIZON ERC Grants

Coordinator

FONDAZIONE BRUNO KESSLER

• Net EU contribution: € 1 493 750,00
• Address: Via santa croce 77 ; 38122 Trento ; Italy
• Region: Nord-Est › Provincia Autonoma di Trento › Trento
• Activity type: Research Organisations
• Other funding: € 0,00