Jifunze la Uimarishaji la Usimamizi dhaifu
Jifunze la uimarishaji la usimamizi dhaifu (WSRL) hufunza mawakala katika mazingira ambapo ishara ya thawabu haina ukamilifu, ni adimu, imecheleweshwa, au ina habari kidogo tu — tofauti na RL kamili ya usimamizi. Wakala lazima ajifunze sera zenye ufanisi licha ya maoni yasiyo kamili, akitumia ishara saidizi, uundaji wa mfumo wa thawabu, au ujifunzaji wa mapendeleo ili kufidia usimamizi dhaifu.
Soma mbinu kamili
Ingia kwa akaunti ya bure ili kusoma sehemu hii.
Method map
The neighbourhood of related methods — select a node to explore.
Vyanzo
- Sutton, R. S. & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. ISBN: 978-0-262-03924-6
- Christiano, P., Leike, J., Brown, T. B., Martic, M., Legg, S. & Amodei, D. (2017). Deep reinforcement learning from human preferences. Advances in Neural Information Processing Systems (NeurIPS), 30. link ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 3). Weakly Supervised Reinforcement Learning. ScholarGate. https://scholargate.app/sw/deep-learning/weakly-supervised-reinforcement-learning
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- Jifunze kwa Kuimarisha (Reinforcement Learning)Ujifunzaji wa Kina↔ compare
- Ujifunzaji wa Uimarishaji Unaojisimamia KwenyeweUjifunzaji wa Kina↔ compare
- Msisimko wa usaidizi wa kujifunza (Semi-supervised Reinforcement Learning)Ujifunzaji wa Kina↔ compare
Imerejelewa na
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →