An opponent striatal circuit for distributional reinforcement learning.

• Tác giả: Jan Drugowitsch, Adam S Lowet, Sara Matias, Melissa Meng, Naoshige Uchida, Qiao Zheng
• Ngôn ngữ: eng
• Thông tin xuất bản: England : Nature , 2025
• Bộ sưu tập: NCBI
• ID: 722013

Tóm tắt

Machine learning research has achieved large performance gains on a wide range of tasks by expanding the learning target from mean rewards to entire probability distributions of rewards-an approach known as distributional reinforcement learning (RL)