Sotabase

Career

· Co-director Of The Delft AI BIOlab, Technische Universiteit Delft2021–
· Assistant Professor, Technische Universiteit Delft2020–
· Stipendary Lecturer In Computer Science, St Anne's College, University of Oxford2018–2020
· Postdoctoral Researcher, University of Oxford2018–2020
· Postdoc, Technische Universität Berlin2017–2017
· PHD Student, Technische Universität Berlin2009–2016
· Diploma, Computer Science, Technische Universität Berlin2000–2008

Publications (39)

Deep Coordination Graphs
International Conference on Machine Learning · 2019
196
cited
Multi-Agent Common Knowledge Reinforcement Learning
Neural Information Processing Systems · 2018
117
cited
My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control
International Conference on Learning Representations · 2020
101
cited
Transient Non-stationarity and Generalisation in Deep Reinforcement Learning
International Conference on Learning Representations · 2020
98
cited
Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control
arXiv.org · 2020
96
cited
Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations
KI - Künstliche Intelligenz · 2015
69
cited
UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning
International Conference on Machine Learning · 2020
59
cited
Optimistic Exploration even with a Pessimistic Initialisation
International Conference on Learning Representations · 2020
48
cited
Generalized Off-Policy Actor-Critic
Neural Information Processing Systems · 2019
43
cited
Neural systems for choice and valuation with counterfactual learning signals
NeuroImage · 2014
37
cited
The effect of novelty on reinforcement learning.
Progress in Brain Research · 2013
37
cited
Deep Residual Reinforcement Learning
Adaptive Agents and Multi-Agent Systems · 2019
35
cited
The Impact of Non-stationarity on Generalisation in Deep Reinforcement Learning
arXiv.org · 2020
35
cited
Multitask Soft Option Learning
Conference on Uncertainty in Artificial Intelligence · 2019
26
cited
Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning
arXiv.org · 2019
25
cited
Construction of approximation spaces for reinforcement learning
Journal of machine learning research · 2013
23
cited
Generating feature spaces for linear algorithms with regularized sparse kernel slow feature analysis
Machine-mediated learning · 2012
21
cited
Multi-Agent Hierarchical Reinforcement Learning with Dynamic Termination
Adaptive Agents and Multi-Agent Systems · 2019
18
cited
Regularized Sparse Kernel Slow Feature Analysis
ECML/PKDD · 2011
17
cited
Interaction of Instrumental and Goal-Directed Learning Modulates Prediction Error Representations in the Ventral Striatum
Journal of Neuroscience · 2016
14
cited
Sotabase