Travelled to:1 × Australia
1 × Canada
3 × USA
Collaborated with:M.L.Littman R.Parr J.Pazis ∅ C.Guestrin
Talks about:learn (5) reinforc (3) algorithm (2) select (2) action (2) procedur (1) classifi (1) satisfi (1) leverag (1) coordin (1)
Person: Michail G. Lagoudakis
DBLP: Lagoudakis:Michail_G=
Contributed to:
200920032002
20012000
1999Wrote 6 papers:
- ICML-2009-PazisL #learning #policy
- Binary action search for learning continuous-action control policies (JP, MGL), pp. 793–800.
- ICML-2003-LagoudakisP #classification #learning
- Reinforcement Learning as Classification: Leveraging Modern Classifiers (MGL, RP), pp. 424–431.
- ICML-2002-GuestrinLP #coordination #learning
- Coordinated Reinforcement Learning (CG, MGL, RP), pp. 227–234.
- SAT-2001-LagoudakisL #branch #learning #satisfiability
- Learning to Select Branching Rules in the DPLL Procedure for Satisfiability (MGL, MLL), pp. 344–359.
- ICML-2000-LagoudakisL #algorithm #learning #using
- Algorithm Selection using Reinforcement Learning (MGL, MLL), pp. 511–518.
- SAC-1999-Lagoudakis #algorithm
- An IDA Algorithm for Optimal Spare Allocation (MGL), pp. 486–488.