ResearchBenchmarksCounterfactual Policy Evaluation on Aircraft Slightly Suboptimal PathCounterfactual Policy Evaluation on Aircraft Slightly Suboptimal PathFollow231Lowest Cumulative RewardICFMDP219.45225.225231236.775Feb 19, 2025Evaluation resultsMethodMethodLinksLowest Cumulative RewardICFMDP2025.02231Gumbel-max2025.02231