元式训练成的智能体实现了贝叶斯最优的智能体

@archillect Memory-based meta-learning is a powerful technique to build agents that adapt fast to any task within a target distribution. A previous theoretical study has argued that this remarkable performance is because the meta-training protocol incentivises agents to behave Bayes-optimally. We empirically investigate this claim on a number of prediction and bandit tasks. Inspired by … Continue reading 元式训练成的智能体实现了贝叶斯最优的智能体