Adrian Sosic

Dr. Adrian Šošić

Postdoc

Rundeturmstrasse 12
64283 Darmstadt

Office: S3/19 1.2

+49 6151 16-57240
+49 6151 16-57241


back

About

Adrian Sosic joined BCS Group in October 2018.

Publications

Exportieren als [feed] Atom [feed] RSS 1.0 [feed] RSS 2.0
Group by: Publikationsjahr | Item type | No grouping
Jump to: 2019 | 2018 | 2017 | 2016 | 2014 | 2012
Number of items: 15.

2019

Alt, B. ; Šošić, A. ; Koeppl, H. (2019):
Correlation Priors for Reinforcement Learning.
In: 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Kanada, 09.12.-13.12.2019, [Konferenzveröffentlichung]

Hüttenrauch, M. ; Šošić, A. ; Neumann, G. (2019):
Deep Reinforcement Learning for Swarm Systems.
In: Journal of Machine Learning Research, S. 1-31, 20, (54), [Online-Edition: http://jmlr.csail.mit.edu/papers/volume20/18-476/18-476.pdf],
[Article]

2018

Šošić, A. ; Zoubir, A. M. ; Koeppl, H. (2018):
A Bayesian Approach to Policy Recognition and State Representation Learning.
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, S. 1295-1308, 40, (6), DOI: 10.1109/TPAMI.2017.2711024,
[Online-Edition: https://doi.org/10.1109/TPAMI.2017.2711024],
[Article]

Šošić, A. ; Zoubir, A. M. ; Koeppl, H. (2018):
Reinforcement Learning in a Continuum of Agents.
In: Swarm Intelligence, S. 23-51, 12, (1), DOI: 10.1007/s11721-017-0142-9,
[Online-Edition: http://rdcu.be/wKay],
[Article]

Šošić, A. ; Zoubir, A. M. ; Koeppl, H. (2018):
Inverse Reinforcement Learning via Nonparametric Subgoal Modeling.
In: AAAI Spring Symposium on Data-Efficient Reinforcement Learning, [Online-Edition: https://aaai.org/ocs/index.php/SSS/SSS18/paper/view/17531/15...],
[Konferenzveröffentlichung]

Šošić, A. ; Rueckert, E. ; Peters, J. ; Zoubir, A. M. ; Koeppl, H. (2018):
Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling.
In: Journal of Machine Learning Research, S. 1-45, 19, (69), [Online-Edition: http://www.jmlr.org/papers/volume19/18-113/18-113.pdf],
[Article]

Hüttenrauch, M. ; Šošić, A. ; Neumann, G. (2018):
Local Communication Protocols for Learning Complex Swarm Behaviors With Deep Reinforcement Learning.
In: International Conference on Swarm Intelligence, [Konferenzveröffentlichung]

Šošić, A. (2018):
Learning Models of Behavior From Demonstration and Through Interaction.
Darmstadt, Technische Universität, [Online-Edition: https://tuprints.ulb.tu-darmstadt.de/8107],
[PhD thesis]

2017

Hüttenrauch, M. ; Šošić, A. ; Neumann, G. (2017):
Guided Deep Reinforcement Learning for Swarm Systems.
In: AAMAS Workshop on Autonomous Robots and Multirobot Systems, [Online-Edition: https://arxiv.org/abs/1709.06011],
[Konferenzveröffentlichung]

Šošić, A. ; KhudaBukhsh, W. R. ; Zoubir, A. M. ; Koeppl, H. (2017):
Inverse Reinforcement Learning in Swarm Systems (Best Paper Award Finalist).
In: International Conference on Autonomous Agents and Multiagent Systems, [Online-Edition: http://dl.acm.org/citation.cfm?id=3091320],
[Konferenzveröffentlichung]

Šošić, A. ; KhudaBukhsh, W. R. ; Zoubir, A. M. ; Koeppl, H. (2017):
Inverse Reinforcement Learning in Swarm Systems.
In: AAMAS Workshop on Transfer in Reinforcement Learning, [Konferenzveröffentlichung]

2016

Šošić, A. ; Zoubir, A. M. ; Koeppl, H. (2016):
Policy Recognition via Expectation Maximization.
In: IEEE International Conference on Acoustics, Speech and Signal Processing, DOI: 10.1109/ICASSP.2016.7472589,
[Online-Edition: https://doi.org/10.1109/icassp.2016.7472589],
[Konferenzveröffentlichung]

Hüttenrauch, M. ; Šošić, A. ; Neumann, G. (2016):
Guided Deep Reinforcement Learning for Swarm Systems.
In: NIPS Workshop on Learning, Inference and Control of Multi-Agent Systems, [Konferenzveröffentlichung]

2014

Guthier, T. ; Šošić, A. ; Willert, V. ; Eggert, J. (2014):
sNN-LDS: Spatio-temporal Non-negative Sparse Coding for Human Action Recognition.
In: Artificial Neural Networks and Machine Learning – ICANN 2014, Springer International Publishing, S. 185-192, [Online-Edition: http://dx.doi.org/10.1007/978-3-319-11179-7_24],
[Book section]

2012

Guthier, T. ; Šošić, A. ; Willert, V. ; Eggert, J. (2012):
Finding a Tradeoff between Compression and Loss in Motion Compensated Video Coding.
In: SIGMAP and WINSYS 2012 - Proceedings of the International Conference on Signal Processing and Multimedia Applications and International Conference on Wireless Information Networks and Systems, Rome, Italy, 24-27 July, 2012, SIGMAP is part of ICETE - The I, [Konferenzveröffentlichung]

This list was generated on Wed Oct 16 06:31:27 2019 CEST.