[Solomonov Seminar] 63. Solomonov seminar

[Marko Grobelnik]

Vabim vas na 63. Solomonov seminar, ki bo
skupaj s Seminarjem Slovenskega drustva za umetno inteligenco (SLAIS)

v torek, 4.12.2001 ob 13.uri v veliki predavalnici IJS.

V strojem ucenju sta dve pomembni podpodrocji, t.i.
"vzpodbujevalno ucenje" (angl. Reinforcement Learning) in
"relacijsko ucenje", ki ima korenine (in tudi precej debla)
v t.i. "induktivnem logicnem progrmiranju". 
Na tokratnem seminarju nam bo gost iz Belgije predstavil
enoten pogled na obe podrocji. Predavanje zna biti se posebej
zanimivo zaradi uvoda v "vzpodbujevalno ucenje", ki pri
nas nikoli ni bilo posebej doma.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Kurt Driessens:
Relational Reinforcement Learning

This talk will present an introduction to reinforcement learning and
relational reinforcement learning.  I will give an overview of the
fundamental principles and techniques of reinforcement learning
without involving a rigorous deduction of the mathematics involved
through the use of some example applications. Then, relational
reinforcement learning will be presented as a combination of
reinforcement learning with relational learning. Its advantages
--- such as the possibility of using structural representations,
making abstraction from specific goals pursued and exploiting
the results of previous learning phases --- will be discussed.