arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0712.4318cs.AI
收藏

概率分布下期望效用的收敛性

Convergence of Expected Utilities with Algorithmic Probability Distributions

Temple University(天普大学);Cornell University(康奈尔大学)

Peter de Blanc

摘要:

我们考虑一个智能体与一个未知的环境进行交互。环境是将自然数映射到自然数的函数;代理关于环境的假设集合包含所有可计算的并且与已知输入输出对的有限集合兼容的这样的函数,并且代理为每个这样的假设分配正概率。我们并不要求这个概率分布是可计算的,但它必须由一个正的可计算函数来限制。智能体对来自环境的输出具有效用函数。我们表明,如果这个效用函数是有界的绝对值以下的一个无界的可计算的功能,那么任何输入的预期效用是未定义的。这意味着一个可计算的效用函数将具有收敛的期望效用当且仅当该函数是有界的。

英文摘要:

We consider an agent interacting with an unknown environment. The environment is a function which maps natural numbers to natural numbers; the agent's set of hypotheses about the environment contains all such functions which are computable and compatible with a finite set of known input-output pairs, and the agent assigns a positive probability to each such hypothesis. We do not require that this probability distribution be computable, but it must be bounded below by a positive computable function. The agent has a utility function on outputs from the environment. We show that if this utility function is bounded below in absolute value by an unbounded computable function, then the expected utility of any input is undefined. This implies that a computable utility function will have convergent expected utilities iff that function is bounded.

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。

↑