Reinforcement learning beyond the Bellman equation: Exploring critic objectives using evolution

Reinforcement learning beyond the Bellman equation: Exploring critic objectives using evolution
复制标题

DOI:
10.1162/isal_a_00338
复制
发表时间:
2020-07
期刊:
--
影响因子:
--
通讯作者:
A. Leite;Madhavun Candadai;E. Izquierdo
A. Leite;Madhavun Candadai;E. Izquierdo
中科院分区:
其他
文献类型:
--
作者:
A. Leite;Madhavun Candadai;E. Izquierdo

文献摘要

相似文献

生物体在多个时间尺度上学习:进化学习和个体终身学习。这两种学习模式是互补的:通过进化发展的先天表型。
Living organisms learn on multiple time scales: evolutionary as well as individual-lifetime learning. These two learning modes are complementary: the innate phenotypes developed through evolution s...