ResearchBenchmarksInverse Transition Learning on Randomworlds 40% stochastic-policy statesInverse Transition Learning on Randomworlds 40% stochastic-policy statesFollow76Epsilon MatchingITL28.1640.585365.42Nov 7, 2024Evaluation resultsMethodMethodLinksEpsilon MatchingEpsilon Matching TransferBest Matching ScoreBest Matching TransferTime/IterationsTotal VariationValue CVaR (1%)Value CVaR (2%)Value CVaR (5%)Number of Constraints ViolatedITL2024.11765058370.65102.02-404.02-397.26-366.430BITL2024.11753857265,561123.3-423.21-398.25-364.340MCE2024.115446383436.61111.08-522.35-514.69-459.7111.81MLE2024.11434629340111.07-525.94-519.63-481.9817.23PS2024.11303119202.61127.02-452.19-444.69-434.2411.66