IQ-Flow: Mechanism Design for Inducing Cooperative Behavior to Self-Interested Agents in Sequential Social Dilemmas

TL;DR

IQ-Flow introduces a novel incentive mechanism that aligns self-interested and cooperative behaviors in multi-agent systems, improving cooperation without assumptions on agents' policies across various environments.

Contribution

The paper presents IQ-Flow, a generalizable offline incentive design framework that aligns self-interest and cooperation in multi-agent reinforcement learning without prior policy assumptions.

Findings

IQ-Flow outperforms existing incentive algorithms in Escape Room and 2-Player Cleanup environments.

IQ-Flow significantly improves cooperation over shared reward setups.

The method generalizes across different environments and agent policies.

Abstract

Achieving and maintaining cooperation between agents to accomplish a common objective is one of the central goals of Multi-Agent Reinforcement Learning (MARL). Nevertheless in many real-world scenarios, separately trained and specialized agents are deployed into a shared environment, or the environment requires multiple objectives to be achieved by different coexisting parties. These variations among specialties and objectives are likely to cause mixed motives that eventually result in a social dilemma where all the parties are at a loss. In order to resolve this issue, we propose the Incentive Q-Flow (IQ-Flow) algorithm, which modifies the system's reward setup with an incentive regulator agent such that the cooperative policy also corresponds to the self-interested policy for the agents. Unlike the existing methods that learn to incentivize self-interested agents, IQ-Flow does not make any assumptions about agents' policies or learning algorithms, which enables the generalization of the developed framework to a wider array of applications. IQ-Flow performs an offline evaluation of the optimality of the learned policies using the data provided by other agents to determine cooperative and self-interested policies. Next, IQ-Flow uses meta-gradient learning to estimate how policy evaluation changes according to given incentives and modifies the incentive such that the greedy policy for cooperative objective and self-interested objective yield the same actions. We present the operational characteristics of IQ-Flow in Iterated Matrix Games. We demonstrate that IQ-Flow outperforms the state-of-the-art incentive design algorithm in Escape Room and 2-Player Cleanup environments. We further demonstrate that the pretrained IQ-Flow mechanism significantly outperforms the performance of the shared reward setup in the 2-Player Cleanup environment.