Seguir
Goran Radanović
Goran Radanović
Research Group Leader, Max Planck Institute for Software Systems
E-mail confirmado em mpi-sws.org - Página inicial
Título
Citado por
Citado por
Ano
How do fairness definitions fare? Examining public attitudes towards algorithmic definitions of fairness
NA Saxena, K Huang, E DeFilippis, G Radanovic, DC Parkes, Y Liu
Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, 99-106, 2019
2312019
A robust bayesian truth serum for non-binary signals
G Radanovic, B Faltings
Proceedings of the AAAI Conference on Artificial Intelligence 27 (1), 833-839, 2013
1492013
Policy teaching via environment poisoning: Training-time adversarial attacks against reinforcement learning
A Rakhsha, G Radanovic, R Devidze, X Zhu, A Singla
International Conference on Machine Learning, 7974-7984, 2020
1382020
Calibrated fairness in bandits
Y Liu, G Radanovic, C Dimitrakakis, D Mandal, DC Parkes
arXiv preprint arXiv:1707.01875, 2017
1302017
Incentives for effort in crowdsourcing using the peer truth serum
G Radanovic, B Faltings, R Jurca
ACM Transactions on Intelligent Systems and Technology (TIST) 7 (4), 1-28, 2016
1182016
Incentives for truthful information elicitation of continuous signals
G Radanovic, B Faltings
Proceedings of the AAAI Conference on Artificial Intelligence 28 (1), 2014
862014
Incentive schemes for participatory sensing
G Radanovic, B Faltings
Proceedings of the 14th international conference on autonomous agents and …, 2015
642015
How do fairness definitions fare? Testing public attitudes towards three algorithmic definitions of fairness in loan allocations
NA Saxena, K Huang, E DeFilippis, G Radanovic, DC Parkes, Y Liu
Artificial Intelligence 283, 103238, 2020
622020
Game theory for data science: Eliciting truthful information
B Faltings, G Radanovic
Springer Nature, 2022
612022
Reinforcement learning for education: Opportunities and challenges
A Singla, AN Rafferty, G Radanovic, NT Heffernan
arXiv preprint arXiv:2107.08828, 2021
502021
Explicable reward design for reinforcement learning agents
R Devidze, G Radanovic, P Kamalaruban, A Singla
Advances in neural information processing systems 34, 20118-20131, 2021
472021
Bayesian fairness
C Dimitrakakis, Y Liu, DC Parkes, G Radanovic
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 509-516, 2019
442019
Diversity in news recommendations
A Bernstein, C De Vreese, N Helberger, W Schulz, K Zweig, C Baden, ...
arXiv preprint arXiv:2005.09495, 2020
432020
Learning to collaborate in markov decision processes
G Radanovic, R Devidze, D Parkes, A Singla
International Conference on Machine Learning, 5261-5270, 2019
392019
Bayesian persuasion in sequential decision-making
J Gan, R Majumdar, G Radanovic, A Singla
Proceedings of the AAAI Conference on Artificial Intelligence 36 (5), 5025-5033, 2022
342022
Incentives for subjective evaluations with private beliefs
G Radanovic, B Faltings
Proceedings of the AAAI Conference on Artificial Intelligence 29 (1), 2015
342015
Defense against reward poisoning attacks in reinforcement learning
K Banihashem, A Singla, G Radanovic
arXiv preprint arXiv:2102.05776, 2021
322021
Multi-view decision processes: the helper-ai problem
C Dimitrakakis, DC Parkes, G Radanovic, P Tylkin
Advances in neural information processing systems 30, 2017
312017
Policy teaching in reinforcement learning via environment poisoning attacks
A Rakhsha, G Radanovic, R Devidze, X Zhu, A Singla
Journal of Machine Learning Research 22 (210), 1-45, 2021
282021
Admissible policy teaching through reward design
K Banihashem, A Singla, J Gan, G Radanovic
Proceedings of the AAAI Conference on Artificial Intelligence 36 (6), 6037-6045, 2022
152022
O sistema não pode executar a operação agora. Tente novamente mais tarde.
Artigos 1–20