K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs

TL;DR

K-SHAP is a novel clustering algorithm that identifies and groups anonymous agent policies from state-action data in multi-agent systems, enhancing understanding of agent behaviors without requiring identity labels.

Contribution

The paper introduces K-SHAP, a new policy clustering method that leverages SHAP explanations and imitation learning to distinguish agent strategies in anonymous multi-agent data.

Findings

Outperforms existing methods in synthetic market data

Effectively identifies different agent strategies in real-world financial data

Provides interpretable explanations for agent behaviors

Abstract

Learning agent behaviors from observational data has shown to improve our understanding of their decision-making processes, advancing our ability to explain their interactions with the environment and other agents. While multiple learning techniques have been proposed in the literature, there is one particular setting that has not been explored yet: multi agent systems where agent identities remain anonymous. For instance, in financial markets labeled data that identifies market participant strategies is typically proprietary, and only the anonymous state-action pairs that result from the interaction of multiple market participants are publicly available. As a result, sequences of agent actions are not observable, restricting the applicability of existing work. In this paper, we propose a Policy Clustering algorithm, called K-SHAP, that learns to group anonymous state-action pairs according to the agent policies. We frame the problem as an Imitation Learning (IL) task, and we learn a world-policy able to mimic all the agent behaviors upon different environmental states. We leverage the world-policy to explain each anonymous observation through an additive feature attribution method called SHAP (SHapley Additive exPlanations). Finally, by clustering the explanations we show that we are able to identify different agent policies and group observations accordingly. We evaluate our approach on simulated synthetic market data and a real-world financial dataset. We show that our proposal significantly and consistently outperforms the existing methods, identifying different agent strategies.