Keywords
sun'iy intellek
agent,
mukofot,
siyosat,
How to Cite
Abstract
Ushbu ilmiy maqolada sun'iy intellekt (SI)ning eng kuchli yo'nalishlaridan biri bo'lgan Mustahkamlovchi o'rganish (Reinforcement Learning, RL) va uning o'yinlardan to real dunyo tizimlarini boshqarishgacha bo'lgan qo'llanilishi har tomonlama tahlil qilinadi. Boshqa mashinaviy o'rganish usullaridan farqli o'laroq, mustahkamlovchi o'rganishda agent o'z muhiti bilan sinov va xato orqali o'zaro ta'sirlashib, mukofotlar tizimi rahbarligida optimal xulq-atvorni o'rganadi.
References
1. Sutton, R. S., & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press.
2. Mnih, V., et al. (2015). "Human-level control through deep reinforcement learning." Nature.
3. Silver, D., et al. (2016). "Mastering the game of Go with deep neural networks and tree search." Nature.
4. Silver, D., et al. (2017). "Mastering the game of Go without human knowledge." Nature.
5. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press
This work is licensed under a Creative Commons Attribution 4.0 International License.
