Probing Dec-POMDP Reasoning in Cooperative MARL

TL;DR

This paper introduces diagnostic tools to evaluate whether current cooperative MARL benchmarks genuinely require Dec-POMDP reasoning, revealing that many do not, and highlights the need for more rigorous environment design.

Contribution

The authors develop a diagnostic suite combining performance comparisons and information-theoretic probes to assess behavioral complexity in MARL benchmarks.

Findings

Many benchmarks do not require true Dec-POMDP reasoning.

Reactive policies often match memory-based agents' performance.

Emergent coordination is often based on brittle synchronous actions.

Abstract

Cooperative multi-agent reinforcement learning (MARL) is typically framed as a decentralised partially observable Markov decision process (Dec-POMDP), a setting whose hardness stems from two key challenges: partial observability and decentralised coordination. Genuinely solving such tasks requires Dec-POMDP reasoning, where agents use history to infer hidden states and coordinate based on local information. Yet it remains unclear whether popular benchmarks actually demand this reasoning or permit success via simpler strategies. We introduce a diagnostic suite combining statistically grounded performance comparisons and information-theoretic probes to audit the behavioural complexity of baseline policies (IPPO and MAPPO) across 37 scenarios spanning MPE, SMAX, Overcooked, Hanabi, and MaBrax. Our diagnostics reveal that success on these benchmarks rarely requires genuine Dec-POMDP reasoning. Reactive policies match the performance of memory-based agents in over half the scenarios, and emergent coordination frequently relies on brittle, synchronous action coupling rather than robust temporal influence. These findings suggest that some widely used benchmarks may not adequately test core Dec-POMDP assumptions under current training paradigms, potentially leading to over-optimistic assessments of progress. We release our diagnostic tooling to support more rigorous environment design and evaluation in cooperative MARL.