• Danil Provodin, Pratik Gajane, Mykola Pechenizkiy and Maurits Kaptein. Provably Efficient Exploration in Constrained Reinforcement Learning: Posterior Sampling Is All You Need.
• Pratik Gajane, Akrati Saxena, Maryam Tavakol, George Fletcher, Mykola Pechenizkiy. Survey on Fair Reinforcement Learning: Theory and Practice.
• Pratik Gajane, Ronald Ortner, Peter Auer, Csaba Szepesvari. Autonomous exploration for navigating in non-stationary CMPs.

• Pratik Gajane. Adversarial Multi-dueling Bandits. In the Workshop on Models of Human Feedback for AI Alignment at ICML 2024.

• Ronald C. van den Broek, Rik Litjens, Tobias Sagis, Luc Siecker, Nina Verbeeke and Pratik Gajane. Multi-Armed Bandits with Generalized Temporally-Partitioned Rewards. In the proceedings of the Symposium on Intelligent Data Analysis (IDA), 2024.

• Jiong Li and Pratik Gajane. Curiosity-driven Exploration in Sparse-reward Multi-agent Reinforcement Learning. In the 16th European Workshop on Reinforcement Learning (EWRL), 2023.

• Ronald C. van den Broek, Rik Litjens, Tobias Sagis, Luc Siecker, Nina Verbeeke and Pratik Gajane. Generalizing distribution of partial rewards for multi-armed bandits with temporally-partitioned rewards. In the 16th European Workshop on Reinforcement Learning (EWRL), 2023.

• Rosa van Tuijn, Tianqin Lu, Emma Driesse, Koen Franken, Pratik Gajane and Emilia Barakova. WeHeart: A Personalized Recommendation Device for Physical Activity Encouragement and Preventing “Cold Start” in Cardiac Rehabilitation. In the proceedings of the 19th International Conference on Human-Computer Interaction (INTERACT), 2023.

• Pratik Gajane, Peter Auer and Ronald Ortner. Autonomous Exploration for Navigating in MDPs using Blackbox RL Algorithms. In the proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI), 2023.

• Dennis Collaris, Pratik Gajane, Joost Jorritsma, Jarke J. van Wijk and Mykola Pechenizkiy. LEMON: Alternative Sampling for More Faithful Explanation through Local Surrogate Models. In the proceedings of the 21st Symposium on Intelligent Data Analysis (IDA), 2023 (Runner-up Frontier prize). Python package.

• Rosa van Tuijn, Tianqin Lu, Emma Driesse, Koen Franken, Pratik Gajane and Emilia Barakova. WeHeart: A Personalized Recommendation Device for Physical Activity Encouragement and Preventing “Cold Start” in Cardiac Rehabilitation (Extended Abstract). In the second International Conference on Hybrid Human-Artificial Intelligence, 2023.

• Pratik Gajane. Local Differential Privacy for Sequential Decision Making in a Changing Environment. In AAAI Privacy-Preserving Artificial Intelligence (PPAI), 2023.

• Danil Provodin, Pratik Gajane, Mykola Pechenizkiy and Maurits Kaptein. An Empirical Evaluation of Posterior Sampling for Constrained Reinforcement Learning. In the Reinforcement Learning for Real Life Workshop at NeurIPS, 2022.

• Danil Provodin, Pratik Gajane, Mykola Pechenizkiy and Maurits Kaptein. The Impact of Batch Learning in Stochastic Linear Bandits. In the proceedings of the 22nd International Conference on Data Mining (ICDM), 2022.

• Danil Provodin, Pratik Gajane, Mykola Pechenizkiy and Maurits Kaptein. The Impact of Batch Learning in Stochastic Bandits. In the Workshop on Ecological Theory of Reinforcement Learning at NeurIPS, 2021.

• Filipo Studzinski Perotto, Sattar Vakili, Pratik Gajane, Yaser Faghan and Mathieu Bourgais. Gambler Bandits and the Regret of Being Ruined. In the proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS) , 2021.

• Ronald Ortner, Pratik Gajane and Peter Auer. Variational Regret Bounds for Reinforcement Learning. In the proceedings of the 35th Conference on Uncertainty in Artificial Intelligence (UAI), 2019. (Poster).

• Peter Auer, Yifang Chen, Pratik Gajane, Chung-Wei Lee, Haipeng Luo, Ronald Ortner and Chen-Yu Wei. Achieving Optimal Dynamic Regret for Non-stationary Bandits without Prior Information. In the proceedings of the 32nd Annual Conference on Learning Theory (COLT), 2019.

• Peter Auer, Pratik Gajane and Ronald Ortner. Adaptively Tracking the Best Bandit Arm with an Unknown Number of Distribution Changes. In the proceedings of the 32nd Annual Conference on Learning Theory (COLT), 2019.

• Pratik Gajane, Ronald Ortner and Peter Auer. A Sliding-Window Approach for Reinforcement Learning in MDPs with Arbitrarily Changing Rewards and Transitions. In the 2nd workshop for Lifelong Learning: A Reinforcement Learning Approach (LLARLA), 2018 (won the best paper award). (Poster).

• Pratik Gajane and Mykola Pechenizkiy. On Formalizing Fairness in Prediction with Machine Learning. In the 5th Workshop on Fairness, Accountability, and Transparency in Machine Learning (FAT/ML), 2018. (Poster).

• Peter Auer, Pratik Gajane and Ronald Ortner. Adaptively Tracking the Best Bandit Arm with an Unknown Number of Distribution Changes. In the 14th European Workshop on Reinforcement Learning (EWRL), 2018. (Poster).

• Pratik Gajane, Emilie Kaufmann and Tanguy Urvoy. Corrupt Bandits for Preserving Local Privacy. In the proceedings of the 29th International Conference on Algorithmic Learning Theory (ALT), 2018.

• Carolin Lawrence, Pratik Gajane and Stefan Riezler. Counterfactual Learning for Machine Translation: Degeneracies and Solutions. In the workshop for Causal Inference and Machine Learning for Intelligent Decision Making, 2017. (Poster).

• Pratik Gajane, Emilie Kaufmann and Tanguy Urvoy. Corrupt bandits. In the 13th European Workshop on Reinforcement Learning (EWRL), 2016. (Poster).

• Pratik Gajane, Tanguy Urvoy and Fabrice Clerot. A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits. In the proceedings of the 32nd International Conference on Machine Learning (ICML), 2015.

• Pratik Gajane and Tanguy Urvoy. Utility-based Dueling Bandits as a Partial Monitoring Game. In the 12th European Workshop on Reinforcement Learning (EWRL), 2015.

Here’s my PhD thesis.