A Regulation Enforcement Solution for Multi-agent Reinforcement Learning

Human behaviors are regularized by a variety of norms or regulations, either to maintain orders or to enhance social welfare. However, if artificially intelligent (AI) agents make decisions on behalf of human beings, it is possible that an AI agent can opt to disobey the regulations (being defective) for self-interests. In this paper, we aim to answer the following question: In a decentralized environment (no centralized authority can control agents), given that not all agents are compliant to regulations at first, can we develop a mechanism such that it is in the self-interest of non-compliant agents to comply after all. We first introduce the problem as Regulation Enforcement and formulate it using reinforcement learning and game theory. Then we propose our solution based on the key idea that although we could not alter how defective agents choose to behave, we can, however, leverage the aggregated power of compliant agents to boycott the defective ones. We conducted simulated experiments on two scenarios: Replenishing Resource Management Dilemma and Diminishing Reward Shaping Enforcement, using deep multi-agent reinforcement learning algorithms. We further use empirical game-theoretic analysis to show that the method alters the resulting empirical payoff matrices in a way that promotes compliance (making mutual compliant a Nash Equilibrium).