Why Greatness Cannot Be Planned

By Kenneth O. Stanley, Joel Lehman. 2015

84 citations recorded by the source corpus.

Subfields: Global and Planetary Change, Reproductive Medicine, Sociology and Political Science

How researchers see this paper

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

In Global and Planetary Change

In Reproductive Medicine

In Sociology and Political Science

Citations in the corpus

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, methodology): “…(Wagner and Altenberg, 1996; Pigliucci, 2008; Lehman and Stanley, 2013), the encoding of genetic information through the genotype-phenotype mapping processes (Hornby et al., 2002), and novelty search and the deception of ﬁtness objectives (Lehman and Stanley, 2008; Stanley and Lehman, 2015).”
Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning (2020, background): “Carbon accounting can be all-expansive, so we focus on a narrow definition provided by Stechemesser and Guenther (2012): “carbon accounting at the project scale can be defined as the measuring and non-monetary valuation of carbon and GHG emissions and offsetting from projects, and the monetary asses”
Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions (2019, background): “If the skills learned in the latter environment apply, it could revolutionize the behavior in the former, reflecting the fact that the most promising stepping stone to the best possible outcome may not be the current top performer in that environment [34, 36, 54].”
Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning (2017, methodology): “…problems, using a ﬁtness function to deﬁne a particular objective and relying only on the optimization of this function may not be eﬃcient: indeed, there may be unknown complex successive stepping-stones that need to be reached before the ﬁnal objective can be approached Stanley and Lehman (2015).”
AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence (2019, background): “Stanley and Lehman provide a colorful example in the uselessness of, for example, trying to select for human-level intelligence by starting with bacteria and selecting for those that perform better on IQ tests [166].”
Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions (2020, methodology): “…Microwaves were invented not by food-heating researchers but by those studying radar; and computers were not invented by optimizing the abacus to increase computations per second, but because scientists invented vacuum tubes and electricity for entirely unrelated purposes (Stanley & Lehman, 2015).”