Supervised reinforcement learning in discrete environment domains

Boris Jensen; Daniel Ortiz-Arroyo; Nareli Cruz-Cortés; Francisco Rodríguez-Henríquez

doi:10.1109/NABIC.2010.5716276

Supervised reinforcement learning in discrete environment domains

Boris Jensen, Daniel Ortiz-Arroyo, Nareli Cruz-Cortés, Francisco Rodríguez-Henríquez

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

This paper describes a supervised reinforcement learning-based model for discrete environment domains. The model was tested within the domain of backgammon game. Our results show that a supervised actor-critic based learning model is capable of improving the initial performance and then eventually reach similar performance levels as those obtained by TD-Gammon, an artificial neural network player (ANN) trained by temporal differences.

Original language	English
Title of host publication	Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010
Pages	215-220
Number of pages	6
DOIs	https://doi.org/10.1109/NABIC.2010.5716276
State	Published - 2010
Externally published	Yes
Event	2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010 - Kitakyushu, Japan Duration: 15 Dec 2010 → 17 Dec 2010

Publication series

Name	Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010

Conference

Conference	2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010
Country/Territory	Japan
City	Kitakyushu
Period	15/12/10 → 17/12/10

Keywords

Actorcritic
Automata player
Machine learning
Reinforcement learning

Access to Document

10.1109/NABIC.2010.5716276

Cite this

Jensen, B., Ortiz-Arroyo, D., Cruz-Cortés, N., & Rodríguez-Henríquez, F. (2010). Supervised reinforcement learning in discrete environment domains. In Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010 (pp. 215-220). Article 5716276 (Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010). https://doi.org/10.1109/NABIC.2010.5716276

@inproceedings{67419c706ac44201b8716f5334101854,

title = "Supervised reinforcement learning in discrete environment domains",

abstract = "This paper describes a supervised reinforcement learning-based model for discrete environment domains. The model was tested within the domain of backgammon game. Our results show that a supervised actor-critic based learning model is capable of improving the initial performance and then eventually reach similar performance levels as those obtained by TD-Gammon, an artificial neural network player (ANN) trained by temporal differences.",

keywords = "Actorcritic, Automata player, Machine learning, Reinforcement learning",

author = "Boris Jensen and Daniel Ortiz-Arroyo and Nareli Cruz-Cort{\'e}s and Francisco Rodr{\'i}guez-Henr{\'i}quez",

year = "2010",

doi = "10.1109/NABIC.2010.5716276",

language = "Ingl{\'e}s",

isbn = "9781424473762",

series = "Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010",

pages = "215--220",

booktitle = "Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010",

note = "2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010 ; Conference date: 15-12-2010 Through 17-12-2010",

}

Jensen, B, Ortiz-Arroyo, D, Cruz-Cortés, N & Rodríguez-Henríquez, F 2010, Supervised reinforcement learning in discrete environment domains. in Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010., 5716276, Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010, pp. 215-220, 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010, Kitakyushu, Japan, 15/12/10. https://doi.org/10.1109/NABIC.2010.5716276

Supervised reinforcement learning in discrete environment domains. / Jensen, Boris; Ortiz-Arroyo, Daniel; Cruz-Cortés, Nareli et al.
Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010. 2010. p. 215-220 5716276 (Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Supervised reinforcement learning in discrete environment domains

AU - Jensen, Boris

AU - Ortiz-Arroyo, Daniel

AU - Cruz-Cortés, Nareli

AU - Rodríguez-Henríquez, Francisco

PY - 2010

Y1 - 2010

N2 - This paper describes a supervised reinforcement learning-based model for discrete environment domains. The model was tested within the domain of backgammon game. Our results show that a supervised actor-critic based learning model is capable of improving the initial performance and then eventually reach similar performance levels as those obtained by TD-Gammon, an artificial neural network player (ANN) trained by temporal differences.

AB - This paper describes a supervised reinforcement learning-based model for discrete environment domains. The model was tested within the domain of backgammon game. Our results show that a supervised actor-critic based learning model is capable of improving the initial performance and then eventually reach similar performance levels as those obtained by TD-Gammon, an artificial neural network player (ANN) trained by temporal differences.

KW - Actorcritic

KW - Automata player

KW - Machine learning

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=79952753576&partnerID=8YFLogxK

U2 - 10.1109/NABIC.2010.5716276

DO - 10.1109/NABIC.2010.5716276

M3 - Contribución a la conferencia

AN - SCOPUS:79952753576

SN - 9781424473762

T3 - Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010

SP - 215

EP - 220

BT - Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010

T2 - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010

Y2 - 15 December 2010 through 17 December 2010

ER -

Jensen B, Ortiz-Arroyo D, Cruz-Cortés N, Rodríguez-Henríquez F. Supervised reinforcement learning in discrete environment domains. In Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010. 2010. p. 215-220. 5716276. (Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010). doi: 10.1109/NABIC.2010.5716276

Supervised reinforcement learning in discrete environment domains

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this