On formalizing fairness in prediction with machine learning P Gajane, M Pechenizkiy the 5th Workshop on Fairness, Accountability, and Transparency in Machine …, 2018 | 287 | 2018 |
Adaptively tracking the best bandit arm with an unknown number of distribution changes P Auer, P Gajane, R Ortner Conference on Learning Theory, 138-158, 2019 | 137 | 2019 |
Variational regret bounds for reinforcement learning R Ortner, P Gajane, P Auer Uncertainty in Artificial Intelligence, 81-90, 2020 | 70 | 2020 |
A sliding-window algorithm for markov decision processes with arbitrarily changing rewards and transitions P Gajane, R Ortner, P Auer Lifelong Learning: A Reinforcement Learning Approach Workshop at FAIM, 2018 | 53 | 2018 |
A relative exponential weighing algorithm for adversarial utility-based dueling bandits P Gajane, T Urvoy, F Clérot International Conference on Machine Learning, 218-227, 2015 | 48 | 2015 |
Corrupt bandits for preserving local privacy P Gajane, T Urvoy, E Kaufmann Algorithmic Learning Theory, 387-412, 2018 | 42 | 2018 |
Achieving optimal dynamic regret for non-stationary bandits without prior information P Auer, Y Chen, P Gajane, CW Lee, H Luo, R Ortner, CY Wei Conference on Learning Theory, 159-163, 2019 | 33 | 2019 |
Adaptively tracking the best arm with an unknown number of distribution changes P Auer, P Gajane, R Ortner European Workshop on Reinforcement Learning 14, 375, 2018 | 31 | 2018 |
Corrupt bandits P Gajane, T Urvoy, E Kaufmann EWRL, 2016 | 16 | 2016 |
Survey on fair reinforcement learning: Theory and practice P Gajane, A Saxena, M Tavakol, G Fletcher, M Pechenizkiy arXiv preprint arXiv:2205.10032, 2022 | 15 | 2022 |
Utility-based dueling bandits as a partial monitoring game P Gajane, T Urvoy In the 12th European Workshop on Reinforcement Learning (EWRL), 2015, 2015 | 7 | 2015 |
Lemon: Alternative sampling for more faithful explanation through local surrogate models D Collaris, P Gajane, J Jorritsma, JJ van Wijk, M Pechenizkiy International Symposium on Intelligent Data Analysis, 77-90, 2023 | 6 | 2023 |
The impact of batch learning in stochastic linear bandits D Provodin, P Gajane, M Pechenizkiy, M Kaptein 2022 IEEE International Conference on Data Mining (ICDM), 1149-1154, 2022 | 5 | 2022 |
Gambler bandits and the regret of being ruined FS Perotto, S Vakili, P Gajane, Y Faghan, M Bourgais 20th International Conference on Autonomous Agents and Multiagent Systems …, 2021 | 5 | 2021 |
Curiosity-driven Exploration in Sparse-reward Multi-agent Reinforcement Learning J Li, P Gajane 16th European Workshop on Reinforcement Learning (EWRL), 2023 | 4 | 2023 |
Autonomous exploration for navigating in non-stationary CMPs P Gajane, R Ortner, P Auer, C Szepesvari arXiv preprint arXiv:1910.08446, 2019 | 4 | 2019 |
Counterfactual learning for machine translation: Degeneracies and solutions C Lawrence, P Gajane, S Riezler arXiv preprint arXiv:1711.08621, 2017 | 4 | 2017 |
Corrupt bandits for privacy preserving input P Gajane, T Urvoy, E Kaufmann arXiv preprint arXiv:1708.05033, 2017 | 3 | 2017 |
WeHeart: A Personalized Recommendation Device for Physical Activity Encouragement and Preventing “Cold Start” in Cardiac Rehabilitation PGEB Rosa van Tuijn, Tianqin Lu, Emma Driesse, Koen Franken Human-Computer Interaction – INTERACT 2023. 14144 (Lecture Notes in Computer …, 2023 | 2* | 2023 |
The impact of batch learning in stochastic bandits D Provodin, P Gajane, M Pechenizkiy, M Kaptein Workshop on Ecological Theory of Reinforcement Learning, 2021 | 2 | 2021 |