Ujifunzaji wa Kina wa Uimarishaji
Deep Reinforcement Learning huunganisha mitandao ya neva na ujifunzaji wa uimarishaji ili wakala ajifunze kwa kuingiliana na mazingira, maarufu kupitia kazi ya Mnih na wenzake ya 2015 katika jarida la Nature kuhusu udhibiti wa kiwango cha binadamu wa michezo ya Atari. Badala ya kujifunza kutoka kwa seti ya data iliyowekwa lebo, wakala huchukua hatua, huzingatia tuzo, na hatua kwa hatua huunda sera inayoongeza faida ya muda mrefu.
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
- Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI: 10.1038/nature14236 ↗
- Schulman, J. et al. (2017). Proximal Policy Optimization Algorithms. arXiv:1707.06347. link ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 1). Deep Reinforcement Learning (DQN / PPO / A3C). ScholarGate. https://scholargate.app/sw/deep-learning/deep-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.
- Utafutaji wa Usanifu wa NeuralUjifunzaji wa Kina↔ compare
- Msitu NasibuUjifunzaji wa Mashine↔ compare
- Mtandao wa Nyuro UnaojirudiaUjifunzaji wa Kina↔ compare
- XGBoostUjifunzaji wa Mashine↔ compare
Imerejelewa na
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →