Marcello Restelli

Available identifiers

zbMath Open restelli.marcelloDBLP64/1011WikidataQ86581313 ScholiaQ86581313MaRDI QIDQ747250

List of research outcomes

Publication	Date of Publication	Type
Interpretable linear dimensionality reduction based on bias-variance analysis	2024-09-20	Paper
Risk-averse optimization of reward-based coherent risk measures	2023-06-19	Paper
Smoothing policies and safe policy gradients	2023-06-12	Paper
https://portal.mardi4nfdi.de/entity/Q5053314	2022-12-06	Paper
Risk-averse policy optimization via risk-neutral policy optimization	2022-10-04	Paper
Policy space identification in configurable environments	2022-08-10	Paper
Online joint bid/daily budget optimization of Internet advertising campaigns	2022-04-11	Paper
Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems	2022-01-28	Paper
https://portal.mardi4nfdi.de/entity/Q5159396	2021-10-27	Paper
https://portal.mardi4nfdi.de/entity/Q4999027	2021-07-09	Paper
https://portal.mardi4nfdi.de/entity/Q4969257	2020-10-05	Paper
Sliding-Window Thompson Sampling for Non-Stationary Settings	2020-06-26	Paper
Budgeted Multi-Armed Bandit in Continuous Action Space	2018-07-12	Paper
Improving multi-armed bandit algorithms in online pricing settings	2018-06-22	Paper
Multi-objective reinforcement learning through continuous Pareto manifold approximation	2016-10-27	Paper
Policy gradient in Lipschitz Markov decision processes	2015-10-23	Paper
Reinforcement distribution in fuzzy Q-learning	2009-11-17	Paper
Reinforcement Distribution in Continuous State Action Space Fuzzy Q–Learning: A Novel Approach	2009-07-02	Paper
Concepts and Fuzzy Models for Behavior-Based Robotics	2007-09-24	Paper
https://portal.mardi4nfdi.de/entity/Q3047003	2004-08-12	Paper
https://portal.mardi4nfdi.de/entity/Q3047214	2004-08-12	Paper
https://portal.mardi4nfdi.de/entity/Q4799278	2003-03-18	Paper

Research outcomes over time

This page was built for person: Marcello Restelli