Learning to Be

By John Baldacchino. 2014

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. James Harrison
2. Percy Liang
3. Marco Pavone
4. Apoorva Sharma
5. Martin Bringmann
6. Marc Pollefeys
7. Paroma Varma
8. Philipp Lindenberger

Citations in the corpus

• Training Classifiers with Natural Language Explanations (2018, methodology): “Semantic parsing of natural language into logical forms is recognized as a challenging problem and has been studied extensively (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Liang et al., 2011; Liang, 2016).”
• Continuous Meta-Learning without Tasks (2019, background): “While these terms are often used interchangeably and inconsistently, they all roughly correspond to the problem of learning within a streaming series of tasks, wherein it is desirable to re-use information from previous tasks while avoiding negative transfer French (1999); Thrun & Pratt (2012).”
• Democratizing technology: pleasure, utility and expressiveness in DIY and maker practice (2013, background): “Previous research in HCI has looked at sharing in DIY communities, including [28, 46, 48].”
• LightGlue: Local Feature Matching at Light Speed (2023, methodology): “Baselines: We extract up to 4096 features with Super-Point and match them with SuperGlue, SGMNet [8], Clus-terGNN [65], and LightGlue with adaptive depth and width.”