1 × Canada
1 × China
1 × France
1 × Israel
1 × USA
∅ R.Ortner A.Khaleghi K.Lakshmanan O.Maillard P.Nguyen
learn (3) reinforc (2) regret (2) bound (2) undiscount (1) represent (1) asymptot (1) process (1) continu (1) consist (1)
Person: Daniil Ryabko
Wrote 5 papers:
- ICML-2015-LakshmananOR #bound #learning
- Improved Regret Bounds for Undiscounted Continuous Reinforcement Learning (KL, RO, DR), pp. 524–532.
- ICML-c1-2014-KhaleghiR #consistency #estimation
- Asymptotically consistent estimation of the number of change points in highly dependent time series (AK, DR), pp. 539–547.
- ICML-c1-2013-MaillardNOR #bound #learning #representation
- Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning (OAM, PN, RO, DR), pp. 543–551.
- ICML-2010-Ryabko #clustering #process
- Clustering processes (DR), pp. 919–926.
- ICML-2004-Ryabko #learning #online
- Online learning of conditionally I.I.D. data (DR).