| Entropy-based prioritized sampling in deep Q-learning M Ramicic, A Bonarini 2017 2nd international conference on image, vision and computing (ICIVC …, 2017 | 20 | 2017 |
| Correlation minimizing replay memory in temporal-difference reinforcement learning M Ramicic, A Bonarini Neurocomputing 393, 91-100, 2020 | 14 | 2020 |
| Attention-based experience replay in deep q-learning M Ramicic, A Bonarini Proceedings of the 9th international conference on machine learning and …, 2017 | 9 | 2017 |
| Augmented memory replay in reinforcement learning with continuous control M Ramicic, A Bonarini IEEE Transactions on Cognitive and Developmental Systems 14 (2), 485-496, 2021 | 8 | 2021 |
| Uncertainty maximization in partially observable domains: A cognitive perspective M Ramicic, A Bonarini Neural Networks 162, 456-471, 2023 | 6 | 2023 |
| Towards learning agents with personality traits: Modeling openness to experience M Ramicic, A Bonarini Cognitive Systems Research 55, 124-134, 2019 | 6 | 2019 |
| Selective perception as a mechanism to adapt agents to the environment: An evolutionary approach M Ramicic, A Bonarini IEEE Transactions on Cognitive and Developmental Systems 12 (1), 64-72, 2019 | 4 | 2019 |
| Informed sampling of prioritized experience replay M Ramicic, V Smidl, A Bonarini 2022 IEEE International Conference on Development and Learning (ICDL), 215-222, 2022 | 2 | 2022 |
| Adaptation of learning agents through artificial perception M Ramicic, A Bonarini Adaptive Behavior 28 (2), 79-88, 2020 | 1 | 2020 |
| Perception as behaviour inducing mechanism: a reinforcement learning perspective M Ramicic Politecnico di Milano, 2019 | | 2019 |
| Smart phone 3D interface control the intelligent model of solar house Ž Stanković, G Radić, M Ramičić Applied Mechanics and Materials 513, 4392-4395, 2014 | | 2014 |
Andrea BonariniFull Professor, Politecnico di Milano, Dipartimento di Eletronica, Informazione e Biongegneria, AIPatvirtintas el. paštas polimi.it