Adrian Šošić

A Bayesian Approach to Policy Recognition and State Representation Learning

Heinz Koeppl, Abdelhak M. Zoubir, Adrian Šošić, 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Guided Deep Reinforcement Learning for Robot Swarms Guided Deep Reinforcement Learning

A. Zoubir, Adrian Šošić, Tag der Einreichung, 2016 .

Policy recognition via expectation maximization

Heinz Koeppl, Abdelhak M. Zoubir, Adrian Sosic, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Deep Reinforcement Learning for Swarm Systems

Gerhard Neumann, Maximilian Hüttenrauch, Adrian Sosic, 2018, J. Mach. Learn. Res..

Reinforcement learning in a continuum of agents

Heinz Koeppl, Abdelhak M. Zoubir, Adrian Sosic, 2018, Swarm Intelligence.

Inverse Reinforcement Learning in Swarm Systems pdf

Heinz Koeppl, Abdelhak M. Zoubir, Adrian Sosic, 2016, AAMAS.

Local Communication Protocols for Learning Complex Swarm Behaviors with Deep Reinforcement Learning

Gerhard Neumann, Maximilian Hüttenrauch, Adrian Sosic, 2017, ANTS Conference.

Guided Deep Reinforcement Learning for Swarm Systems pdf

Gerhard Neumann, Maximilian Hüttenrauch, Adrian Sosic, 2017, ArXiv.

Correlation Priors for Reinforcement Learning

Adrian Šošić, H. Koeppl, Bastian Alt, 2019, NeurIPS.

Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling

Heinz Koeppl, Abdelhak M. Zoubir, Jan Peters, 2018, J. Mach. Learn. Res..