arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1312.6726cs.AI
收藏

变化环境中的有限理性决策

Bounded Rational Decision-Making in Changing Environments

Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Max Planck Institute for Biolog. Cybernetics(马克斯·普朗克生物控制论研究所)

Jordi Grau-Moya, Daniel A. Braun

摘要:

一个完全理性的决策者从一组可能的行动中选择具有最高效用增益的最佳行动。描述这种决策过程的最优性原则并没有考虑寻找最优行动的计算成本。有限理性决策通过专门权衡信息处理成本和预期效用来解决这个问题。有趣的是,在描述热力学系统的变化时,也会出现能量和熵之间的类似权衡。这种相似性最近被用来描述有界理性代理。至关重要的是,这个框架假设在决策者计算最优策略时,环境不会发生变化。当这一要求没有得到满足时,决策者将遭受效用的低效率,这是因为当前的政策对于过去的环境是最优的。在这里,我们借用非平衡态热力学的概念来量化这些低效率,并与模拟说明其与计算资源的关系。

英文摘要:

A perfectly rational decision-maker chooses the best action with the highest utility gain from a set of possible actions. The optimality principles that describe such decision processes do not take into account the computational costs of finding the optimal action. Bounded rational decision-making addresses this problem by specifically trading off information-processing costs and expected utility. Interestingly, a similar trade-off between energy and entropy arises when describing changes in thermodynamic systems. This similarity has been recently used to describe bounded rational agents. Crucially, this framework assumes that the environment does not change while the decision-maker is computing the optimal policy. When this requirement is not fulfilled, the decision-maker will suffer inefficiencies in utility, that arise because the current policy is optimal for an environment in the past. Here we borrow concepts from non-equilibrium thermodynamics to quantify these inefficiencies and illustrate with simulations its relationship with computational resources.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑