Knowledge Growth in an Artificial Animal
By Stewart W. Wilson. 1985
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
- Marc G. Bellemare
- Marlos C. Machado
- Michael H. Bowling
- Matthew J. Hausknecht
- Sergey Levine
- Erik Talvitie
- Joel Veness
- Yuxi Li
Citations in the corpus
- Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents (2017, background): “One traditional goal in reinforcement learning is for agents to continually improve their performance as they obtain more data (Hutter, 2005; Ring, 1997; Singh, Barto, & Chentanez, 2004; Sutton et al., 2011; Thrun & Mitchell, 1993; Wilson, 1985).”
- Hierarchical Chunking in Classifier Systems (2008, methodology): “Reactive CSs have been extensively used for theoretical and experimental studies (e.g., see Wilson, 1985; Grefenstette, 1988), and they are also taken as a basis for the work described in this paper.”
- Learning classifier systems: a complete introduction, review, and roadmap (2009, methodology): “, the new rule “0#110#0-01” might be generated from the input string 0011010) [44].”
- Hierarchical Chunking in Classifier Systems (1994, background): “There are many variants of the BBA -e.g., see (Dorigo, 1991; Huang, 1989; Riolo, 1990; Wei& 1991; Wilson, 1985, 1987) -as well as of the PSP -e.g., see (Grefenstette, 1988; Holland & Reitman, 1978; Wei& 1992).”
- The Neurally Controlled Animat: Biological Brains Acting with Simulated Bodies (2001, background): “…the Neurally-Controlled Animat approach, that uses multi-electrode array (MEA) culture dishes (Thomas et al., 1972; Gross, 1979; Pine, 1980) to record neural activity from populations of neurons and use that activity to control an artificial animal, also called an Animat (Wilson, 1985, 1987) (Fig.”
- Letter recognition using Holland-style adaptive classifiers (2004, methodology): “The simplification of the "standard" Holland approach used for this application is very similar to the modifications made by others for studies on category learning (Wilson, 1985, 1987, 1988, Davis & Young, 1988).”