220 citations
- University of GrazAT3 papers
- Humboldt-Universität zu BerlinDE2 papers
- Institute of Physics BelgradeRS2 papers
- Johannes Kepler University of LinzAT2 papers
- Centre Inria de l'Université de LilleFR1 paper
- Centre National de la Recherche ScientifiqueFR1 paper
- Data61AU1 paper
- Indian Institute of Technology BombayIN1 paper
- Institut de Mathématiques de ToulouseFR1 paper
- Institute of PhysicsPL1 paper
- Isfahan University of TechnologyIR1 paper
- Leibniz University HannoverDE1 paper
Showing 2013 · cs.LGShow all
2 papers · 2 filters
cs.LG2013★ 20 cited
Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning
Odalric-Ambrym Maillard, Phuong Nguyen, Ronald Ortner +1
We consider an agent interacting with an environment in a single stream of actions, observations, and rewards, with no reset. This process is not assumed to be a Markov Decision Pr…
cs.LG2013★ 44 cited
Online Regret Bounds for Undiscounted Continuous Reinforcement Learning
Ronald Ortner, Daniil Ryabko
We derive sublinear regret bounds for undiscounted reinforcement learning in continuous state space. The proposed algorithm combines state aggregation with the use of upper confide…