Building Machines that Learn and Think for Themselves: Commentary on Lake et al., Behavioral and Brain Sciences, 2017
By Matthew Botvinick, David G. T. Barrett, Peter W. Battaglia, Nando de Freitas, Dharshan Kumaran, Joel Z. Leibo, Timothy P. Lillicrap, Joseph Modayil, S. Mohamed, Neil C. Rabinowitz and 9 more. 2017
38 citations recorded by the source corpus.
We agree with Lake and colleagues on their list of key ingredients for building humanlike intelligence, including the idea that model-based reasoning is essential. However, we favor an approach that centers on one additional ingredient: autonomy. In particular, we aim toward agents that can both build and exploit their own internal models, with minimal human hand-engineering. We believe an approach centered on autonomous learning has the greatest chance of success as we scale toward real-world complexity, tackling domains for which ready-made formal models are not available. Here we survey several important examples of the progress that has been made toward building autonomous agents with humanlike abilities, and highlight some outstanding challenges.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sergey Levine
- Yoshua Bengio
- Ruslan Salakhutdinov
- Josh Tenenbaum
- Mohit Bansal
- Pieter Abbeel
- J. Urgen Schmidhuber
- Quoc V. Le
Citations in the corpus
- Machine Theory of Mind (2018, background): “Rather, we focus on the problem of how an observer could learn autonomously how to model other agents using limited data (Botvinick et al., 2017).”
- Measuring abstract reasoning in neural networks (2018, background): “Though there has also been substantial progress in both reasoning and abstract representation learning in neural nets (Botvinick et al., 2017; LeCun et al., 2015; Higgins et al., 2016; 2017), the extent to which these models exhibit anything like general abstract reasoning is the subject of much deb”
- AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence (2019, background): “Additionally, people will pursue hybrid approaches (e.g. the vision outlined in Botvinick et al. [16]) and it will be difficult in many cases to tell which path a particular group or project belongs to.”
- The Omniglot Challenge: A 3-Year Progress Report (2019, background): “[14], Davis and Marcus [15], Hansen et al.”