Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making

Stelios Triantafyllou, Aleksa Sukovic, Yasaman Zolfimoselo, Goran Radanovic

Keywords: counterfactual reasoning, causal explanation formula, multi-agent Markov decision processes

TL;DR: We introduce a novel causal explanation formula that decomposes the counterfactual effect of an agent's action by attributing to each agent and state variable in an MMDP a score reflecting its respective contribution to the effect.

Abstract: We address the challenge of explaining counterfactual outcomes in multi-agent Markov decision processes. In particular, we aim to explain the total counterfactual effect of an agent's action to some realized outcome through its influence on the environment dynamics and the agents' behavior. To achieve this, we introduce a novel causal explanation formula that decomposes the counterfactual effect of an agent's action by attributing to each agent and state variable a score reflecting its respective contribution to the effect.

Submission Number: 20