Epstein Secrets

tational resources. And as we have argued in detail in Chapter 7, efficiency is not a side-issue but rather the essence of real-world AGI (since as Hutter has shown, if one casts efficiency aside, arbitrary levels of general intelligence can be achieved via a trivially simple program). The essence of

nce with respect to the distribution v over the space of all computable reward-summable environ- ments, E, that is, TOO a L v(Ii)1'; PEE Legg and Hutter's universal intelligence is obtained by setting v equal to the universal distribution. This framework is more flexible than it might seem. E.g. sup

r the various cognitively-relevant properties of the environment from looking at data about the ev- eryday world. We agree in principle, and in fact Ben Kuipers and his colleagues have done some interesting work in this direction, showing that learning algorithms can infer some basics about the structure of

formance with respect to the distribution v over the space of all computable reward-summable environ- ments, E, that is, Y(m) = SO vr pew Legg and Hutter’s universal intelligence is obtained by setting v equal to the universal distribution. This framework is more flexible than it might seem. E.g. supp

putational resources. And as we have argued in detail in Chapter 7, efficiency is not a side-issue but rather the essence of real-world AGI (since as Hutter has shown, if one casts efficiency aside, arbitrary levels of general intelligence can be achieved via a trivially simple program). The essence of t

er the various cognitively-relevant properties of the environment from looking at data about the ev- eryday world. We agree in principle, and in fact Ben Kuipers and his colleagues have done some interesting work in this direction, showing that learning algorithms can infer some basics about the structure of s

rization of Real-World General Intelligence ......... 135 7.3.1 Biased Universal Intelligence............ 0.00. ee eee 136 7.3.2 Connecting Legg and Hutter’s Model of Intelligent Agents to the Real World... ee cet ete e tne e eens 137 7.3.3 Pragmatic General Intelligence ............ 00... c eee eee 13

igurations that carry out sensorimotor and categorization tasks. The emergence of higher-level cognition from this approach seems rather unlikely. e Ben Kuipers and his colleagues [MK07, MIX08, MIXO09]have pursued an extremely innovative research program which combines qualitative reasoning and reinforcement