Projecten per jaar
Vingerafdruk
- 1 Soortgelijke profielen
Netwerk
Projecten
- 1 Niet gestart
-
FWOTM1108: Besluitvorming in multi-objective multi-agent domeinen met teambeloning
1/10/22 → 30/09/25
Project: Fundamenteel
Onderzoeksoutput
-
A Practical Guide to Multi-Objective Reinforcement Learning and Planning
Hayes, C. F., Radulescu, R., Bargiacchi, E., Källström, J., Macfarlane, M., Reymond, M., Verstraeten, T., Zintgraf, L., Dazeley, R., Heintz, F., Howley, E., Irissappane, A. A., Mannion, P., Nowe, A., De Oliveira Ramos, G., Restelli, M., Vamplew, P. & Roijers, D. M., 13 apr 2022, In : Autonomous Agents and Multi-Agent Systems. 36, 1, 59 blz., 26.Onderzoeksoutput: Article
Open AccessBestand6 Downloads (Pure) -
Commitment and Cyclic Strategies in Multi-Objective Games
Röpke, W., Radulescu, R., Nowe, A. & Roijers, D. M., 2022, (Unpublished). 9 blz.Onderzoeksoutput: Unpublished paper
Bestand2 Downloads (Pure) -
Special issue on adaptive and learning agents 2020
da Silva, F. L., MacAlpine, P., Radulescu, R., Santos, F. P. & Mannion, P., 12 jan 2022, In : Neural Computing & Applications. 34, blz. 1649–1651 3 blz.Onderzoeksoutput: Article
Open Access -
Besluitvorming in systemen met meerdere agenten en objectieven: een op nut gebaseerd perspectief
Radulescu, R., 2021, Brussels.Onderzoeksoutput: PhD Thesis
-
Communication Strategies in Multi-Objective Normal-Form Games
Röpke, W., Radulescu, R., Roijers, D. M. & Nowe, A., 3 mei 2021. 9 blz.Onderzoeksoutput: Unpublished paper
Open AccessBestand41 Downloads (Pure)
Prijzen
-
IBM Award of Scientific Excellence
Mihail Emilov Mihaylov (Recipient), Ivan Razo Zapata (Recipient), Roxana-Teodora Radulescu (Recipient), Sergio Jurado (Recipient), Narcis Avellana (Recipient) & Ann Nowe (Recipient), jun 2016
Prijs: Prize (including medals and awards)
Activiteiten
-
Panel Discussion Chair: Challenges and Opportunities for Real-World Applications of MODeM
Roxana-Teodora Radulescu (Contributor)14 jul 2021Activiteit: Talk or presentation at a workshop/seminar
-
On Nash Equilibria for Multi-Objective Normal Form Games under Scalarised Expected Returns versus Expected Scalarised Returns
Roxana-Teodora Radulescu (Speaker)16 jul 2021Activiteit: Talk or presentation at a workshop/seminar
-
Adaptive and Learning Agents Workshop 2021
Roxana-Teodora Radulescu (Organiser), Diederik M. Roijers (Organiser)3 mei 2021 → 4 mei 2021Activiteit: Participating in or organizing an event at an external academic organisation
-
32nd Benelux Conference on Artificial Intelligence (BNAIC 2020)
Roxana-Teodora Radulescu (Speaker)19 nov 2020 → 20 nov 2020Activiteit: Talk or presentation at a conference
-
Introduction to Reinforcement Learning and Current Developments
Roxana-Teodora Radulescu (Invited speaker)9 nov 2020Activiteit: Talk at an external academic organisation
Scriptie
-
Communication In Multi-Objective Games: A Mixed Game-Theoretic and Reinforcement Learning Approach To Multi-Objective Normal-Form Games
Auteur: Röpke, W., 2021Begeleider: Nowe, A. (Promotor), Roijers, D. M. (Advisor) & Radulescu, R. (Advisor)
Scriptie/masterproef: Master's Thesis
Bestand -
Simulating the Shift Towards Semantic Gender in Dutch: A Multi-Agent Language Game Approach
Auteur: Radulescu, R., 2015Begeleider: Beuls, K. (Promotor)
Scriptie/masterproef: Master's Thesis