Modeling Socially Synergistic Behavior in Autonomous Agents

Abstract

The “Tragedy of the Commons” (TOC) is a problem in which the sustainability of the society (group of agents) reduces due to self-interested individual agents. Many areas of interest to society like climate change, fisheries management, preservation of rainforests exhibit this phenomenon. We have focused on understanding what is the degree of sacrifice that an agent can make so that the sustainability of the society can be extended. For this we first make a mathematical modeling of the TOC dilemma. Next we propose three types of algorithms corresponding to the different behaviors of the agents. First we assume that the agents are interested in their individual gains only. In this case the society survives for the least amount of time. In the second approach we assume that the agents make decisions based on the resource availability, individual gains or a combination of both. Here an agent’s behavior takes into account the welfare of the society to some extent. Thus now the society survives for a longer period of time compared to that in the previous case. In the third approach we define a measure of social awareness of the agents. This measure is indicative of the degree of sacrifice the agent is willing to make. Now the society performs considerably better than the second case. We have experimentally validated these results. Our study shows that if the agents are willing to sacrifice for some period of time, the sustainability of the society increases considerably.