Evolving simple programs for playing atari games
By Dennis G. Wilson, Sylvain Cussat-Blanc, Hervé Luga, Julian Francis Miller. 2018
71 citations recorded by the source corpus.
Cartesian Genetic Programming (CGP) has previously shown capabilities in image processing tasks by evolving programs with a function set specialized for computer vision. A similar approach can be applied to Atari playing. Programs are evolved using mixed type CGP with a function set suited for matrix operations, including image processing, but allowing for controller behavior to emerge. While the programs are relatively small, many controllers are competitive with state of the art methods for the Atari benchmark set and require less training time. By evaluating the programs of the best evolved individuals, simple but effective strategies can be found.
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
- Quoc V. Le
- Chen Liang
- David R. So
- Leslie Pack Kaelbling
- Tomas Lozano-Perez
- Esteban Real
- Sergey Levine
- Ferran Alet
Citations in the corpus
- AutoML-Zero: Evolving Machine Learning Algorithms From Scratch (2020, background): “program parsing [14], and game playing [89], to name a few.”
- Meta-learning curiosity algorithms (2020, background): “…searching over mathematical operations within neural networks (Ramachandran et al., 2017; Gaier & Ha, 2019), searching over programs to solve games (Wilson et al., 2018; Kelly & Heywood, 2017; Silver et al., 2019) and to optimize neural networks (Bengio et al., 1995; Bello et al., 2017), and…”
- Automatic programming: The open issue? (2019, methodology): “com/mgbel lemar e/Arcad e-Learn ing-Envir onmen t, which was recently tackled using Cartesian GP [68] and Tangled Program Graph GP [30].”