Asymptotic non-learnability of universal agents with computable horizon functions

16 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Scalable agent alignment via reward modeling: a research direction (2018, background): “…with a correctly aligned reward function, the resulting behavior might still be unaligned because the agent may fail to converge to an optimal policy: even provably Bayes-optimal agents may fail to converge to the optimal policy due to a lack of exploration (Orseau, 2013; Leike & Hutter, 2015).”
Bad Universal Priors and Notions of Optimality (2015, background): “However, this problem can be alleviated by adding an extra exploration component to AIXI (Lattimore, 2013, Ch. 5), similar to knowledge-seeking agents (Orseau, 2014; Orseau et al., 2013), or by the use of optimism (Sunehag and Hutter, 2012).”