Iti0210w13: erinevus redaktsioonide vahel
Mine navigeerimisribale
Mine otsikasti
Resümee puudub |
|||
| 3. rida: | 3. rida: | ||
Hüvitisega õppimine. ''Q-Learning''. [''AIMA''] 21.3.2, [''ARTINT''] [https://artint.info/2e/html/ArtInt2e.Ch12.S4.html 12.4]. | Hüvitisega õppimine. ''Q-Learning''. [''AIMA''] 21.3.2, [''ARTINT''] [https://artint.info/2e/html/ArtInt2e.Ch12.S4.html 12.4]. | ||
[http://mnemstudio.org/path-finding-q-learning-tutorial.htm | Mõned sissejuhatavad artiklid: [http://mnemstudio.org/path-finding-q-learning-tutorial.htm],[https://blog.valohai.com/reinforcement-learning-tutorial-part-1-q-learning] | ||
[http://www.cse.unsw.edu.au/~cs9417ml/RL1/algorithms.html Q-Learning/SARSA] | [http://www.cse.unsw.edu.au/~cs9417ml/RL1/algorithms.html Q-Learning/SARSA] | ||
Redaktsioon: 28. november 2019, kell 18:17
13. Nädal
Hüvitisega õppimine. Q-Learning. [AIMA] 21.3.2, [ARTINT] 12.4.
Mõned sissejuhatavad artiklid: [1],[2]