Explainable Reinforcement Learning
Explainable Reinforcement Learning (XRL) huongeza mawakala wa kawaida wa reinforcement learning na mbinu zinazofanya sera zao, maamuzi, na tabia zilizojifunzwa zieleweke kwa wanadamu. Badala ya kutibu sera kama kisanduku cheusi, XRL hutoa maelezo ya baada ya ukweli au hujenga sera za uwazi kwa asili, kuwezesha uthibitishaji wa uaminifu, utatuzi wa hitilafu, na uwajibikaji katika utengenezaji wa maamuzi otomatiki wa kiwango cha juu.
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
- Puiutta, E., & Veith, E. M. S. P. (2020). Explainable Reinforcement Learning: A Survey. In Machine Learning and Knowledge Extraction (CD-MAKE 2020), Lecture Notes in Computer Science, vol. 12279, pp. 77–95. Springer. DOI: 10.1007/978-3-030-57321-8_5 ↗
- Explainable artificial intelligence. Wikipedia. link ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 3). Explainable Reinforcement Learning (XRL). ScholarGate. https://scholargate.app/sw/deep-learning/explainable-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.
- Attention MechanismUjifunzaji wa Kina↔ compare
- Ufafanuzi wa Uainishaji wa BERTUjifunzaji wa Kina↔ compare
- Jifunze kwa Kuimarisha (Reinforcement Learning)Ujifunzaji wa Kina↔ compare
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →