A Meta-learning Method Based on Temporal Difference Error
By Kunikazu Kobayashi, Hiroyuki Mizoue, Takashi Kuremoto, Masanao Obayashi. 2009
12 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Cognitive Neuroscience, Control and Systems Engineering
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
- Pieter Abbeel
- Chelsea Finn
- Yuxi Li
- Quoc V. Le
- Yoshua Bengio
- Matthew Botvinick
- Ruslan Salakhutdinov
In Cognitive Neuroscience
- Sergey Levine
- Matthew Botvinick
- Chelsea Finn
- Zeb Kurth-Nelson
- Jane X. Wang
- Eiji Uchibe
- Charles Blundell
- R´emi Munos
In Control and Systems Engineering
- R´emi Munos
- Kenji Doya
- Charles Blundell
- Eiji Uchibe
- Matthew Botvinick
- Dhruva Tirumala
- Bruno Scherrer
- Amir-massoud Farahmand
Citations in the corpus
- Learning to reinforcement learn (2016, background): “…in neuroscience but only in a narrow sense, according to which meta-learning adjusts scalar hyperparameters such as the learning rate or softmax inverse temperature (Khamassi et al., 2011; 2013; Kobayashi et al., 2009; Lee and Wang, 2009; Schweighofer and Doya, 2003; Soltani et al., 2006).”
- Online meta-learning by parallel algorithm competition (2017, methodology): “[17] proposed a meta-learning method based on the absolute values of the TD-errors.”