Imitation Learning of Team-play in Multiagent System based on Hidden Markov Modeling

Noda, Itsuki

Imitation Learning of Team-play in Multiagent System based on Hidden Markov Modeling

Download BibTeX Cite

Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence. Pages 1470-1471.

Abstract

This paper addresses agents' intentions as building blocks of imitation learning that abstract local situations of the agent, and proposes a hierarchical hidden Markov model (HMM) to represent cooperative behaviors of teamworks. The key of the proposed model is introduction of gate probabilities that restrict transition among agents' intentions according to others' intentions. Using these probabilities, the framework can control transitions flexibly among basic behaviors in a cooperative behavior.

Itsuki Noda. 2003. Imitation Learning of Team-play in Multiagent System based on Hidden Markov Modeling. In Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, IJCAI-03. IJCAI, 1470–1471. https://ijcai.org/proceedings/2003/240

@inproceedings{ijcai2003p240,
  title     = {Imitation Learning of Team-play in Multiagent System based on Hidden Markov Modeling},
  author    = {Noda, Itsuki},
  booktitle = {Proceedings of the Eighteenth International Joint Conference on
               Artificial Intelligence, {IJCAI-03}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {Georg Gottlob},
  pages     = {1470--1471},
  year      = {2003},
  url       = {https://ijcai.org/proceedings/2003/240},
}

TY  - CPAPER
TI  - Imitation Learning of Team-play in Multiagent System based on Hidden Markov Modeling
AU  - Noda, Itsuki
T2  - Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, IJCAI-03
PB  - International Joint Conferences on Artificial Intelligence
PY  - 2003
SP  - 1470
EP  - 1471
UR  - https://ijcai.org/proceedings/2003/240
ER  -