Mood modelling within reinforcement learning

Simulating mood within a decision making process has been shown to allow cooperation to occur within the Prisoner’s Dilemma. In this paper we propose how to integrate a mood model into the classical reinforcement learning algorithm Sarsa, and show how this addition can allow self-interested agents to be successful within a multi agent environment. The human-inspired moody agent will learn to cooperate in social dilemmas without the use of punishments or other external incentives. We use both the Prisoner’s Dilemma and the Stag Hunt as our dilemmas. We show that the model provides improvements in both individual payoffs and levels of cooperation within the system when compared to the standard Sarsa model. We also show that the agents’ interaction model and their ability to differentiate between opponents influences how the reinforcement learning process converges.