Preprint
Aug 2026
Policy Optimality Measurement for Multi-Vehicle Decision-Making: From Extrinsic Indicators to Intrinsic Quality
This framework establishes a rigorous, model-agnostic standard for benchmarking intrinsic multi-agent policy quality, and leverages a fully converged Monte Carlo Tree Search as an asymptotic oracle to establish a theoretical ground-truth baseline distribution.
Ye Han, Li-Jun Zhang, D. Meng
· 0 citations