Follow
Adrian Šošić
Adrian Šošić
Senior Data Scientist, Merck KGaA
Verified email at merckgroup.com
Title
Cited by
Cited by
Year
Deep reinforcement learning for swarm systems
M Hüttenrauch, A Šošić, G Neumann
Journal of Machine Learning Research 20 (54), 1-31, 2019
2342019
Guided deep reinforcement learning for swarm systems
M Hüttenrauch, A Šošić, G Neumann
arXiv preprint arXiv:1709.06011, 2017
1332017
Guided deep reinforcement learning for swarm systems
M Hüttenrauch, A Šošić, G Neumann
AAMAS Workshop on Autonomous Robots and Multirobot Systems, 2017
1322017
Guided Deep Reinforcement Learning for Swarm Systems
GN Maximilian Hüttenrauch, Adrian Šošić
NIPS Workshop on Learning, Inference and Control of Multi-Agent Systems, 2016
132*2016
Inverse Reinforcement Learning in Swarm Systems
HK Adrian Šošić, Wasiur R KhudaBukhsh, Abdelhak M Zoubir
AAMAS Workshop on Transfer in Reinforcement Learning, 2017
70*2017
Inverse reinforcement learning in swarm systems
A Šošić, WR KhudaBukhsh, AM Zoubir, H Koeppl
arXiv preprint arXiv:1602.05450, 2016
702016
Local communication protocols for learning complex swarm behaviors with deep reinforcement learning
M Hüttenrauch, A Šošić, G Neumann
Swarm Intelligence: 11th International Conference, ANTS 2018, Rome, Italy …, 2018
362018
Inverse reinforcement learning via nonparametric spatio-temporal subgoal modeling
A Šošić, E Rueckert, J Peters, AM Zoubir, H Koeppl
Journal of Machine Learning Research 19 (69), 1-45, 2018
162018
Correlation priors for reinforcement learning
B Alt, A Šošić, H Koeppl
Advances in neural information processing systems 32, 2019
122019
A Bayesian approach to policy recognition and state representation learning
A Šošić, AM Zoubir, H Koeppl
IEEE Transactions on Pattern Analysis and Machine Intelligence 40 (6), 1295-1308, 2018
122018
Reinforcement learning in a continuum of agents
A Šošić, AM Zoubir, H Koeppl
Swarm Intelligence 12, 23-51, 2018
62018
Inverse reinforcement learning via nonparametric subgoal modeling
A Šošic, AM Zoubir, H Koeppl
AAAI spring symposium on data-efficient reinforcement learning, 2018
62018
Learning complex swarm behaviors by exploiting local communication protocols with deep reinforcement learning
M Hüttenrauch, A Šošić, G Neumann
arXiv preprint arXiv:1709.07224, 2017
62017
Policy recognition via expectation maximization
A Sosic, AM Zoubir, H Koeppl
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
52016
Learning models of behavior from demonstration and through interaction
A Šošić
Technische Universität, 2018
22018
sNN-LDS: spatio-temporal non-negative sparse coding for human action recognition
T Guthier, A Šošić, V Willert, J Eggert
Artificial Neural Networks and Machine Learning–ICANN 2014: 24th …, 2014
22014
Reinforcement learning in a continuum of agents (vol 12, pg 23, 2018)
A Sosic, AM Zoubir, H Koeppl
SWARM INTELLIGENCE 12 (4), 361-361, 2018
2018
Correction to: Reinforcement learning in a continuum of agents
A Šošić, AM Zoubir, H Koeppl
Swarm Intelligence 12, 361-361, 2018
2018
Markov Assumptions for Non-negative Matrix Factorization
A Šošić
2013
Finding a Tradeoff between Compression and Loss in Motion Compensated Video Coding.
T Guthier, A Sosic, V Willert, J Eggert
SIGMAP, 81-84, 2012
2012
The system can't perform the operation now. Try again later.
Articles 1–20