论文标题
学习效率与处理：迈向多任务的规范理论
Efficiency of learning vs. processing: Towards a normative theory of multitasking
论文作者
论文摘要
对人类认知的惊人局限性是我们无法同时执行某些任务。最近的工作表明，这种限制可能是由于网络体系结构的基本权衡而产生的，而网络体系结构的基本权衡是由任务之间的表示形式共享所驱动的：共享促进更快的学习，而牺牲了干扰，同时多任务处理。从这个角度来看，多任务失败可能反映了对学习效率而不是多任务功能的偏爱。我们通过制定理想的贝叶斯代理来探讨这一假设，该贝叶斯代理通过学习任务集的共享或单独表示，从而最大程度地提高了预期奖励。我们调查了代理的行为，并表明在大量参数上，代理人牺牲了长期的最优性（更高的多任务处理能力），以获得短期奖励（更快的学习）。此外，我们构建了一个一般的数学框架，在该框架中，可以检查学习速度和处理效率之间的合理选择，以了解各种不同的任务环境。
A striking limitation of human cognition is our inability to execute some tasks simultaneously. Recent work suggests that such limitations can arise from a fundamental tradeoff in network architectures that is driven by the sharing of representations between tasks: sharing promotes quicker learning, at the expense of interference while multitasking. From this perspective, multitasking failures might reflect a preference for learning efficiency over multitasking capability. We explore this hypothesis by formulating an ideal Bayesian agent that maximizes expected reward by learning either shared or separate representations for a task set. We investigate the agent's behavior and show that over a large space of parameters the agent sacrifices long-run optimality (higher multitasking capacity) for short-term reward (faster learning). Furthermore, we construct a general mathematical framework in which rational choices between learning speed and processing efficiency can be examined for a variety of different task environments.
