Journal papers:


Doctoral dissertations:

Book chapters:

Conference papers:

  • M.S. Stankovic, M. Beko, N Ilic and S.S. Stankovic. Multi-Agent Actor-Critic Multitask Reinforcement Learning based on GTD(1) with Consensus, 61st IEEE Conference on Decision and Control, CDC 2022, Cancun, Mexico, 2022.
  • M. S. Stanković, M. Beko, N. Ilić and S.S. Stanković. “Consensus on the Auxiliary Variables in Distributed Gradient-Based Temporal Difference Algorithms”, 9th International Conference IcETRAN, Novi Pazar, Serbia, June, 2022.
  • M.S. Stanković, M. Beko, M. Pavlović, I. Popadić, S.S. Stanković, “Distributed On-Policy Actor-Critic Reinforcement Learning,” in Sinteza 2022 – International Scientific Conference on Information Technology and Data Related Research, Belgrade, Singidunum University, Serbia, pp. 389-393, 2022.
  • A. Ćuk, U. Dragović, M. Tanasković, N. Bačanin and M.S. Stanković, “Obuka perceptrona hibridizovanom metodom između genetskog algoritma i Firefly algoritma”, YUINFO 2021 Conference, 2021.
  • M. S. Stanković, M. Beko, N. Ilić and S. S. Stanković, “Distributed Multi-Agent Reinforcement Learning Algorithm based on Gradient Correction“, Proc. of 7th IcETRAN, Belgrade, 2020.