泛AI期望效用的收敛性
Convergence of Expected Utility for Universal AI
摘要:
我们考虑一个代理和环境之间的重复交互序列。关于环境的不确定性由假设空间上的概率分布捕获,其中包括所有可计算函数。给定一个效用函数,我们可以评估任何计算策略与环境交互的预期效用。在做了一些合理的假设(也许还有一个不那么合理的假设)之后,我们证明了如果效用函数是无界的,那么任何政策的预期效用都是不确定的。
英文摘要:
We consider a sequence of repeated interactions between an agent and an environment. Uncertainty about the environment is captured by a probability distribution over a space of hypotheses, which includes all computable functions. Given a utility function, we can evaluate the expected utility of any computational policy for interaction with the environment. After making some plausible assumptions (and maybe one not-so-plausible assumption), we show that if the utility function is unbounded, then the expected utility of any policy is undefined.
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。