Sotabase

Career

· Research Scientist, Spotify2021–
· Researcher, Microsoft2018–2021
· Postdoctoral Researcher, Department of Computer Science, University of Oxford2015–2018
· Part-time Postgraduate Teaching Assistant, UCL2013–2013
· Doctor of Philosophy (Ph.D.), Machine Learning / Computer Science, UCL2011–2015
· Intern (Software Development For R D), SAP2009–2009
· Student Employee (Werkstudent), Siemens2009–2009
· Master of Science (M.Sc.), Computer Science, High distinction, GPA: 1.14 (1.00 is best, 5.00 is worst), Technical University Munich2008–2010
· Bachelor of Engineering (B.Eng.), Computer Science, summa cum laude, GPA: 4.94/5.00, Warsaw University of Technology2004–2008
· Bachelor of Arts (B.A.), English, very good, GPA: 4.91/5.00, Wyższa Szkoła Lingwistyczna w Częstochowie2003–2006

Publications (41)

Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
Neural Information Processing Systems · 2019
189
cited
Better Exploration with Optimistic Actor-Critic
Neural Information Processing Systems · 2019
180
cited
Discount Factor as a Regularizer in Reinforcement Learning
International Conference on Machine Learning · 2020
84
cited
Compositional Planning Using Optimal Option Models
International Conference on Machine Learning · 2012
76
cited
Conservative Uncertainty Estimation By Fitting Prior Networks
International Conference on Learning Representations · 2020
63
cited
Multi-task Batch Reinforcement Learning with Metric Learning
Neural Information Processing Systems · 2019
62
cited
Expected Policy Gradients for Reinforcement Learning
Journal of machine learning research · 2018
61
cited
Expected Policy Gradients
AAAI Conference on Artificial Intelligence · 2017
59
cited
Deep Interactive Bayesian Reinforcement Learning via Meta-Learning
Adaptive Agents and Multi-Agent Systems · 2021
55
cited
OFFER: Off-Environment Reinforcement Learning
AAAI Conference on Artificial Intelligence · 2017
53
cited
Evaluating the Robustness of Collaborative Agents
Adaptive Agents and Multi-Agent Systems · 2021
41
cited
Regularized Policies are Reward Robust
International Conference on Artificial Intelligence and Statistics · 2021
28
cited
Information Directed Reward Learning for Reinforcement Learning
Neural Information Processing Systems · 2021
25
cited
Alternating Optimisation and Quadrature for Robust Control
AAAI Conference on Artificial Intelligence · 2016
23
cited
Imitation Learning by Reinforcement Learning
International Conference on Learning Representations · 2021
22
cited
AMRL: Aggregated Memory For Reinforcement Learning
International Conference on Learning Representations · 2020
21
cited
Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay
Knowledge Discovery and Data Mining · 2023
19
cited
DRIFT: Deep Reinforcement Learning for Functional Software Testing
arXiv.org · 2020
16
cited
Fourier Policy Gradients
International Conference on Machine Learning · 2018
15
cited
Value Iteration with Options and State Aggregation
arXiv.org · 2015
11
cited
Sotabase
Kamil Ciosek | Researcher Profile | Sotabase | Sotabase