Travelled to:
1 × China
1 × USA
Collaborated with:
S.Mannor P.Nguyen R.Ortner D.Ryabko
Talks about:
represent (1) reinforc (1) select (1) regret (1) latent (1) bandit (1) state (1) optim (1) learn (1) bound (1)
Person: Odalric-Ambrym Maillard
DBLP: Maillard:Odalric=Ambrym
Contributed to:
Wrote 2 papers:
- ICML-c1-2014-MaillardM
- Latent Bandits (OAM, SM), pp. 136–144.
- 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.