The following publications are possibly variants of this publication:
- Near-optimal Regret Bounds for Reinforcement LearningThomas Jaksch, Ronald Ortner, Peter Auer. jmlr, 11:1563-1600, 2010. [doi]
- Variational Regret Bounds for Reinforcement LearningRonald Ortner, Pratik Gajane, Peter Auer. uai 2018: 16 [doi]
- Optimal Regret Bounds for Selecting the State Representation in Reinforcement LearningOdalric-Ambrym Maillard, Phuong Nguyen, Ronald Ortner, Daniil Ryabko. icml 2013: 543-551 [doi]
- Regret Bounds for Learning State Representations in Reinforcement LearningRonald Ortner, Matteo Pirotta, Alessandro Lazaric, Ronan Fruit, Odalric-Ambrym Maillard. nips 2019: 12717-12727 [doi]
- Logarithmic Online Regret Bounds for Undiscounted Reinforcement LearningPeter Auer, Ronald Ortner. nips 2007: 49-56 [doi]
- Online Regret Bounds for Undiscounted Continuous Reinforcement LearningRonald Ortner, Daniil Ryabko. nips 2012: 1772-1780 [doi]
- Improved Regret Bounds for Undiscounted Continuous Reinforcement LearningK. Lakshmanan, Ronald Ortner, Daniil Ryabko. icml 2015: 524-532 [doi]