Cooperation-eliciting Prisoner's dilemma payoffs for reinforcement learning agents

Koichi Moriyama, Satoshi Kurihara, Masayuki Numao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This work considers a stateless Q-learning agent in iterated Prisoner's Dilemma (PD). We have already given a condition of PD payoffs and Q-learning parameters that helps stateless Q-learning agents cooperate with each other [2]. That condition, however, has a restrictive premise. This work relaxes the premise and shows a new payoff condition for mutual cooperation. After that, we derive the payoff relations that will elicit mutual cooperation from the new condition.

Original languageEnglish
Title of host publication13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages1619-1620
Number of pages2
Volume2
ISBN (Electronic)9781634391313
Publication statusPublished - 2014 Jan 1
Externally publishedYes
Event13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014 - Paris, France
Duration: 2014 May 52014 May 9

Other

Other13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014
CountryFrance
CityParis
Period14/5/514/5/9

Fingerprint

Reinforcement learning

Keywords

  • Game theory
  • Reinforcement learning

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Moriyama, K., Kurihara, S., & Numao, M. (2014). Cooperation-eliciting Prisoner's dilemma payoffs for reinforcement learning agents. In 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014 (Vol. 2, pp. 1619-1620). International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).

Cooperation-eliciting Prisoner's dilemma payoffs for reinforcement learning agents. / Moriyama, Koichi; Kurihara, Satoshi; Numao, Masayuki.

13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014. Vol. 2 International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2014. p. 1619-1620.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Moriyama, K, Kurihara, S & Numao, M 2014, Cooperation-eliciting Prisoner's dilemma payoffs for reinforcement learning agents. in 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014. vol. 2, International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), pp. 1619-1620, 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014, Paris, France, 14/5/5.
Moriyama K, Kurihara S, Numao M. Cooperation-eliciting Prisoner's dilemma payoffs for reinforcement learning agents. In 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014. Vol. 2. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS). 2014. p. 1619-1620
Moriyama, Koichi ; Kurihara, Satoshi ; Numao, Masayuki. / Cooperation-eliciting Prisoner's dilemma payoffs for reinforcement learning agents. 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014. Vol. 2 International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2014. pp. 1619-1620
@inproceedings{7eefd33db1a04f568c71c3c1d962c60b,
title = "Cooperation-eliciting Prisoner's dilemma payoffs for reinforcement learning agents",
abstract = "This work considers a stateless Q-learning agent in iterated Prisoner's Dilemma (PD). We have already given a condition of PD payoffs and Q-learning parameters that helps stateless Q-learning agents cooperate with each other [2]. That condition, however, has a restrictive premise. This work relaxes the premise and shows a new payoff condition for mutual cooperation. After that, we derive the payoff relations that will elicit mutual cooperation from the new condition.",
keywords = "Game theory, Reinforcement learning",
author = "Koichi Moriyama and Satoshi Kurihara and Masayuki Numao",
year = "2014",
month = "1",
day = "1",
language = "English",
volume = "2",
pages = "1619--1620",
booktitle = "13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014",
publisher = "International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)",

}

TY - GEN

T1 - Cooperation-eliciting Prisoner's dilemma payoffs for reinforcement learning agents

AU - Moriyama, Koichi

AU - Kurihara, Satoshi

AU - Numao, Masayuki

PY - 2014/1/1

Y1 - 2014/1/1

N2 - This work considers a stateless Q-learning agent in iterated Prisoner's Dilemma (PD). We have already given a condition of PD payoffs and Q-learning parameters that helps stateless Q-learning agents cooperate with each other [2]. That condition, however, has a restrictive premise. This work relaxes the premise and shows a new payoff condition for mutual cooperation. After that, we derive the payoff relations that will elicit mutual cooperation from the new condition.

AB - This work considers a stateless Q-learning agent in iterated Prisoner's Dilemma (PD). We have already given a condition of PD payoffs and Q-learning parameters that helps stateless Q-learning agents cooperate with each other [2]. That condition, however, has a restrictive premise. This work relaxes the premise and shows a new payoff condition for mutual cooperation. After that, we derive the payoff relations that will elicit mutual cooperation from the new condition.

KW - Game theory

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=84911404219&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84911404219&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84911404219

VL - 2

SP - 1619

EP - 1620

BT - 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014

PB - International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)

ER -