Travelled to:1 × China
1 × Finland
1 × Israel
1 × USA
1 × United Kingdom
Collaborated with:M.Ghavamzadeh R.Munos B.Scherrer M.G.Azar E.Brunskill M.Restelli A.Bonarini M.Geist V.Gabillon M.W.Hoffman
Talks about:analysi (3) sampl (3) learn (3) reinforc (2) classif (2) polici (2) finit (2) iter (2) base (2) algorithm (1)
Person: Alessandro Lazaric
DBLP: Lazaric:Alessandro
Contributed to:
20142012201120102008Wrote 8 papers:
- ICML-c2-2014-AzarLB #correlation #feedback #online #optimisation #probability
- Online Stochastic Optimization under Correlated Bandit Feedback (MGA, AL, EB), pp. 1557–1565.
- ICML-2012-GeistSLG #approach #difference #learning
- A Dantzig Selector Approach to Temporal Difference Learning (MG, BS, AL, MG), p. 49.
- ICML-2011-GabillonLGS #classification #policy
- Classification-based Policy Iteration with a Critic (VG, AL, MG, BS), pp. 1049–1056.
- ICML-2011-GhavamzadehLMH #analysis
- Finite-Sample Analysis of Lasso-TD (MG, AL, RM, MWH), pp. 1177–1184.
- ICML-2010-LazaricG #learning #multi
- Bayesian Multi-Task Reinforcement Learning (AL, MG), pp. 599–606.
- ICML-2010-LazaricGM #algorithm #analysis #classification #policy
- Analysis of a Classification-based Policy Iteration Algorithm (AL, MG, RM), pp. 607–614.
- ICML-2010-LazaricGM10a #analysis
- Finite-Sample Analysis of LSTD (AL, MG, RM), pp. 615–622.
- ICML-2008-LazaricRB #learning
- Transfer of samples in batch reinforcement learning (AL, MR, AB), pp. 544–551.