|
|
|
|
LEADER |
00000cam a22000004i 4500 |
001 |
945962 |
003 |
FI-J |
005 |
20210226124205.0 |
008 |
040915s2004 fi ||||||m |||||||eng|| |
035 |
|
|
|a 945962
|
041 |
0 |
|
|a eng
|
100 |
1 |
|
|a Oltean, Doina.
|
245 |
1 |
0 |
|a Reinforcement learning in artificial intelligence /
|c Doina Oltean.
|
260 |
|
|
|a Jyväskylä,
|c 2004.
|
300 |
|
|
|a 86 lehteä.
|
336 |
|
|
|a teksti
|b txt
|2 rdacontent
|
337 |
|
|
|a käytettävissä ilman laitetta
|b n
|2 rdamedia
|
338 |
|
|
|a nide
|b nc
|2 rdacarrier
|
509 |
|
|
|a Pro gradu -työ :
|c Jyväskylän yliopisto, tietotekniikan laitos.
|9 602.
|
579 |
|
|
|a XLUETTELOITU
|
653 |
|
|
|a Artificial Intelligence (AI)
|
653 |
|
|
|a agent
|
653 |
|
|
|a Reinforcement Learning (RL)
|
653 |
|
|
|a Adaptive Dynamic Programming (ADP)
|
653 |
|
|
|a Temporal Differences (TD)
|
653 |
|
|
|a Q-values
|
999 |
|
|
|c 945962
|d 945962
|
952 |
|
|
|b KANAVUORI
|c 614
|o TIETOTEKN Gradu Oltean
|9 1
|