Travelled to:1 × France
1 × USA
Collaborated with:D.Ryabko K.Lakshmanan O.Maillard P.Nguyen
Talks about:reinforc (2) regret (2) learn (2) bound (2) undiscount (1) represent (1) continu (1) select (1) improv (1) state (1)
Person: Ronald Ortner
DBLP: Ortner:Ronald
Contributed to:
20152013Wrote 2 papers:
- ICML-2015-LakshmananOR #bound #learning
- Improved Regret Bounds for Undiscounted Continuous Reinforcement Learning (KL, RO, DR), pp. 524–532.
- 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.