INTAGS: Interactive Agent-Guided Simulation

TL;DR

This paper introduces INTAGS, a novel framework for creating realistic multi-agent system simulators by optimizing a new metric through reinforcement learning, demonstrated on stock market simulations.

Contribution

The paper proposes a new MAS distance metric and an interactive agent-guided simulation framework that improves the realism of multi-agent system simulators.

Findings

INTAGS produces more realistic simulated data than existing methods.

The framework effectively captures the sequential and interactive nature of MAS.

Demonstrated success in stock market simulation example.

Abstract

In many applications involving multi-agent system (MAS), it is imperative to test an experimental (Exp) autonomous agent in a high-fidelity simulator prior to its deployment to production, to avoid unexpected losses in the real-world. Such a simulator acts as the environmental background (BG) agent(s), called agent-based simulator (ABS), aiming to replicate the complex real MAS. However, developing realistic ABS remains challenging, mainly due to the sequential and dynamic nature of such systems. To fill this gap, we propose a metric to distinguish between real and synthetic multi-agent systems, which is evaluated through the live interaction between the Exp and BG agents to explicitly account for the systems' sequential nature. Specifically, we characterize the system/environment by studying the effect of a sequence of BG agents' responses to the environment state evolution and take such effects' differences as MAS distance metric; The effect estimation is cast as a causal inference problem since the environment evolution is confounded with the previous environment state. Importantly, we propose the Interactive Agent-Guided Simulation (INTAGS) framework to build a realistic ABS by optimizing over this novel metric. To adapt to any environment with interactive sequential decision making agents, INTAGS formulates the simulator as a stochastic policy in reinforcement learning. Moreover, INTAGS utilizes the policy gradient update to bypass differentiating the proposed metric such that it can support non-differentiable operations of multi-agent environments. Through extensive experiments, we demonstrate the effectiveness of INTAGS on an equity stock market simulation example. We show that using INTAGS to calibrate the simulator can generate more realistic market data compared to the state-of-the-art conditional Wasserstein Generative Adversarial Network approach.