| 000 | 00954nam a2200277Ia 4500 | ||
|---|---|---|---|
| 003 | OSt | ||
| 005 | 20221205164205.0 | ||
| 008 | 211118s9999 xx 000 0 und d | ||
| 020 | _a978-1-60845-493-8 | ||
| 040 | _cIITB | ||
| 041 | _aeng | ||
| 100 |
_aNauman, Feliz _921987 _eAuthor |
||
| 245 | 0 | _aAlgorithms for reinforcement learning (e-book) | |
| 260 |
_aSan Rafael _bMorgan and Claypool / _bIEEE Press / _bSpringer _c2010 |
||
| 440 |
_aSynthesis lectures on data management _921986 |
||
| 500 | _aIEEE Morgan and Claypool Computer and Information Science (CIS) collection | ||
| 650 | 0 |
_91269 _aMachine learning |
|
| 650 | 0 |
_912282 _aMarkov processes |
|
| 650 | 0 |
_913744 _aStochastic approximation |
|
| 650 | 0 |
_9705 _aMonte Carlo method |
|
| 650 | 0 |
_94177 _aComputer simulation |
|
| 650 | 0 |
_aNatural gradient _923583 |
|
| 700 |
_aHerschel Melanie _eAuthor _921989 |
||
| 856 | _uhttps://ieeexplore.ieee.org/document/6813120 | ||
| 942 |
_cEB _2udc |
||
| 999 |
_c278336 _d278336 |
||