| 2025 | AISTATS | Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization. | Daniil Tiapkin, Evgenii Chzhen, Gilles Stoltz |
| 2023 | ALT | On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits. | Antoine Barrier, Aurlien Garivier, Gilles Stoltz |
| 2019 | ALT | Uniform regret bounds over R | Pierre Gaillard, Sbastien Gerchinovitz, Malo Huard, Gilles Stoltz |
| 2019 | ICML | Target Tracking for Contextual Bandits: Application to Demand Side Management. | Margaux Brgre, Pierre Gaillard, Yannig Goude, Gilles Stoltz |
| 2014 | COLT | A second-order bound with excess losses. | Pierre Gaillard, Gilles Stoltz, Tim van Erven |
| 2014 | COLT | Approachability in unknown games: Online learning meets multi-objective optimization. | Shie Mannor, Vianney Perchet, Gilles Stoltz |
| 2012 | ALT | Editors' Introduction. | Nader H. Bshouty, Gilles Stoltz, Nicolas Vayatis, Thomas Zeugmann |
| 2011 | ALT | Lipschitz Bandits without the Lipschitz Constant. | Sbastien Bubeck, Gilles Stoltz, Jia Yuan Yu |
| 2009 | ALT | Pure Exploration in Multi-armed Bandits Problems. | Sbastien Bubeck, Rmi Munos, Gilles Stoltz |
| 2009 | COLT | Online Multi-task Learning with Hard Constraints. | Gbor Lugosi, Omiros Papaspiliopoulos, Gilles Stoltz |
| 2007 | COLT | Strategies for Prediction Under Imperfect Monitoring. | Gbor Lugosi, Shie Mannor, Gilles Stoltz |
| 2006 | ITW | Regret Minimization Under Partial Monitoring. | Nicol Cesa-Bianchi, Gbor Lugosi, Gilles Stoltz |
| 2005 | COLT | Improved Second-Order Bounds for Prediction with Expert Advice. | Nicol Cesa-Bianchi, Yishay Mansour, Gilles Stoltz |
| 2004 | COLT | Minimizing Regret with Label Efficient Prediction. | Nicol Cesa-Bianchi, Gbor Lugosi, Gilles Stoltz |
| 2003 | COLT | Internal Regret in On-Line Portfolio Selection. | Gilles Stoltz, Gbor Lugosi |