ICAART.pdf (291.99 kB)
Download file

Augmenting reinforcement learning to enhance cooperation in the iterated prisoner’s dilemma

Download (291.99 kB)
conference contribution
posted on 22.02.2022, 09:18 authored by Grace FeehanGrace Feehan, Syeda FatimaSyeda Fatima
Reinforcement learning algorithms applied to social dilemmas sometimes struggle with converging to mutual cooperation against like-minded partners, particularly when utilising greedy behavioural selection methods. Recent research has demonstrated how affective cognitive mechanisms, such as mood and emotion, might facilitate increased rates of mutual cooperation when integrated with these algorithms. This research has, thus far, primarily utilised mobile multi-agent frameworks to demonstrate this relationship - where they have also identified interaction structure as a key determinant of the emergence of cooperation. Here, we use a deterministic, static interaction structure to provide deeper insight into how a particular moody reinforcement learner might encourage the evolution of cooperation in the Iterated Prisoner’s Dilemma. In a novel grid environment, we both replicated original test parameters and then varied the distribution of agents and the payoff matrix. We found that behavioural trends from past research were present (with suppressed magnitude), and that the proportion of mutual cooperations was heightened when both the influence of mood and the cooperation index of the payoff matrix chosen increased. Changing the proportion of moody agents in the environment only increased mutual cooperations by virtue of introducing cooperative agents to each other.

History

School

  • Science

Department

  • Computer Science

Published in

Proceedings of the 14th International Conference on Agents and Artificial Intelligence

Volume

3

Pages

146 - 157

Source

14th International Conference on Agents and Artificial Intelligence (ICAART 2022)

Publisher

SCITEPRESS - Science and Technology Publications

Version

AM (Accepted Manuscript)

Rights holder

© SCITEPRESS - Science and Technology Publications

Publisher statement

The definitive published version is available at https://doi.org/10.5220/0010787500003116 as an Open Access Article. It is published by SCITEPRESS - Science and Technology Publications under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licence (CC BY-NC-ND 4.0). Full details of this licence are available at: https://creativecommons.org/licenses/by-nc-nd/4.0/

Copyright date

2022

ISBN

9789897585470

Language

en

Editor(s)

Ana Paula Rocha; Luc Steels; Jaap van den Herik

Location

Online

Event dates

3rd February 2022 - 5th February 2022

Depositor

Dr Syeda Fatima. Deposit date: 21 February 2022