Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs
This work addresses the problem of accountable decision-making in multi-agent systems for researchers and practitioners, but it is incremental as it builds on existing causal analysis methods in MDPs.
The paper tackles the challenge of attributing causal effects of agents' actions in multi-agent sequential decision-making by introducing agent-specific effects (ASE) to measure how an agent's action influences outcomes through other agents, and it proposes a sampling-based algorithm for estimation, with experimental evaluation in a sepsis management environment showing utility.
Establishing causal relationships between actions and outcomes is fundamental for accountable multi-agent decision-making. However, interpreting and quantifying agents' contributions to such relationships pose significant challenges. These challenges are particularly prominent in the context of multi-agent sequential decision-making, where the causal effect of an agent's action on the outcome depends on how other agents respond to that action. In this paper, our objective is to present a systematic approach for attributing the causal effects of agents' actions to the influence they exert on other agents. Focusing on multi-agent Markov decision processes, we introduce agent-specific effects (ASE), a novel causal quantity that measures the effect of an agent's action on the outcome that propagates through other agents. We then turn to the counterfactual counterpart of ASE (cf-ASE), provide a sufficient set of conditions for identifying cf-ASE, and propose a practical sampling-based algorithm for estimating it. Finally, we experimentally evaluate the utility of cf-ASE through a simulation-based testbed, which includes a sepsis management environment.