Offer Description

The research programme aims to develop advanced trustworthy reinforcement learning methods for real-world systems, with particular emphasis on planning and tree-search algorithms, including Monte Carlo Tree Search approaches. The activities will involve the design of tree-based models, distance functions and representations for time series, as well as asynchronous, parallel and efficient pipelines for processing large volumes of data and simulations. High-performance software solutions will be investigated and integrated into reproducible and scalable machine learning workflows to support robust decision-making in dynamic and complex environments. The research will include experimental validation, benchmarking, and the analysis of efficiency, generalization and reliability across different real-world application domains, including robotic and energy systems.

Where to apply Website

Requirements

Additional Information

Eligibility criteria

For admission to the selection process, potential candidates must fulfil the following requirements:
a)



Master's Degree [Laurea Magistrale o a ciclo unico awarded pursuant to Art. 3(1n), Ministerial Decree no. 270 of 22/10/04], obtained no more than six years before the expiry date of this call;
b) Possession of a curriculum suitable for assisting in carrying out research activities;
c) Knowledge of the following foreign language: English.

Eligible destination country/ies for fellows:

- Italy

Eligibility of fellows: country/ies of residence:
- AFRICA
- EUROPE
- OCEANIA
- NORTH AMERICA
- SOUTH AMERICA
- ASIA

Eligibility of fellows: nationality/ies:
- AFRICA
- EUROPE
- OCEANIA
- NORTH AMERICA
- SOUTH AMERICA
- ASIA

Selection process

The competition will be carried out by an evaluation of titles and examination by means of an interview.

Website for additional job details

Work Location(s)

Number of offers available 1 Company/Institute Università degli Studi di Verona Country Italy

Contact City

Verona Website

STATUS: EXPIRED

Share this page

📌 Id/26 - Trustworthy reinforcement learning: development of efficient tree search methods for real-world systems (Verona)
🏢 Nessun nome
📍 Verona