The second naive physics manifesto

By P. Hayes. 1995

Subfields: Reinforcement Learning

How researchers see this paper

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

In Reinforcement Learning

1. Yuke Zhu
2. Li Fei-Fei
3. Josh Tenenbaum
4. Murray Shanahan
5. Jeffrey Mark Siskind
6. Michael Beetz
7. Li-Jia Li
8. Justin Johnson

Citations in the corpus

• Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations (2016, background): “It was later proposed that there be a certain plurality to concepts and their related axioms (Hayes, 1985).”
• Towards Deep Symbolic Reinforcement Learning (2016, background): “But the everyday physical world is structured according to many other common sense priors [28, 27, 29, 25, 30].”
• Envisioning the qualitative effects of robot manipulation actions using simulation-based projections (2017, background): “In the context of Naive Physics (Hayes, 1979, 1985), solutions to the problem of egg cracking (Miller and Mor-genstern, 2009), were formulated based on logical axiomatizations (Lifschitz, 1998; Morgenstern, 2001).”
• Intuitive Theories (2020, background): “Characterizing people's intuitive understanding of physics is a challenging task (Hayes, 1985).”
• Grounding language in perception (1993, background): “Hayes 1984 ). The substantiality constraint states that solid objects cannot pass through one another.”