arXiv:2604.23716 · v6
Non-Stationarity Breaks Permutation Surrogates in Multi-Agent Reinforcement Learning: Diagnosis and Remedies
摘要
Reporting guidance for information-theoretic measures is rarely tested against ground truth. We test one guardrail in two multi-agent reinforcement learning games, a social dilemma and a coordination race, over 100 seeds, on agent pairs whose directed influence is zero by construction. Omitting one precondition, the exclusion of the non-stationary training transient, gives false-positive rates of 100.00% and 99.95%, flagging agents that anneal exploration independently, in runs that never met, as influencing one another. Excluding the transient reaches 3.05% in the social dilemma but 11.8% in the coordination game, so exclusion is neither the only treatment nor a sufficient one. The remedy we recommend changes only the null model, permuting the source within blocks of training time, and reaches 5.25% and 5.50%. Of the three remedies compared (exclusion, this surrogate and conditioning on training time), only the surrogate stays at or below the size of the test in both games. Restricted permutation is an established construction, and the contribution lies in measuring it against ground truth. A third null control, four learners in the social dilemma, defeats all three, and raises the rate of conditioning by 15.20 points against 4.55 for ours. With injected links of known strength, the surrogate detects 82.5% where conditioning detects 58.0% on identical pairs, while the test without exclusion reports a positive with or without a link, so its apparent sensitivity is uninformative. Five block counts from 16 to 256 land in the nominal region, and code and data are released.
作者备注:33 pages, 4 figures. Published in IEEE Access (early access), DOI 10.1109/ACCESS.2026.3754039. This version corrects two reference entries and rewrites the abstract for clarity, with every number and claim unchanged. Code and data at https://doi.org/10.5281/zenodo.22658530 and https://github.com/dentros/te-nonstationarity
期刊信息:IEEE Access, 2026