Isbn: 9787111724780 - 正版 强化学习 前沿算法与应用 白辰甲 赵英男 郝建业 刘鹏 震 值函数 策略梯度 值分布建模 算法 多目标 层次化 技能 (1 resultados)

- Tapa blanda
Librería: liu xing, Nanjing, JS, Chinaliu xing
Contactar con el vendedorVendedor de 5 estrellasCondición: Nuevo
EUR 130,52
Envío por EUR 16,07Se envía de China a Estados Unidos de AmericaCantidad disponible: 1 disponible
paperback. Condición: New. Paperback. Pub Date: 2023-05 Pages: 304 Publisher: China Machine Press Reinforcement learning is an important branch of machine learning and an important way to achieve general artificial intelligence. This book introduces the rapid development of reinforcement learning at the algorithm level. including basic algorithms such as value function. policy gradient. value distribution modeling. and algorithms based on model learning. exploration and utilization. multi-objective learning. hierarchic.…