Travelled to:1 × Finland
1 × USA
Collaborated with:N.Roy J.Pineau D.Wingate J.B.Tenenbaum A.Geramifard J.Redding J.P.How
Talks about:reinforc (2) learn (2) discoveri (1) bayesian (1) network (1) infinit (1) featur (1) depend (1) pomdp (1) onlin (1)
Person: Finale Doshi
DBLP: Doshi:Finale
Contributed to:
20112008Wrote 3 papers:
- ICML-2011-DoshiWTR #infinity #network
- Infinite Dynamic Bayesian Networks (FD, DW, JBT, NR), pp. 913–920.
- ICML-2011-GeramifardDRRH #dependence #online
- Online Discovery of Feature Dependencies (AG, FD, JR, NR, JPH), pp. 881–888.
- ICML-2008-DoshiPR #learning #using
- Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs (FD, JP, NR), pp. 256–263.