ResearchBenchmarksOffline Reinforcement Learning on Multimodal HRI board game datasetOffline Reinforcement Learning on Multimodal HRI board game datasetFollow29.75Mean ScoreNFQ-1.59566.542214.6822.8178Sep 21, 2025Evaluation resultsMethodMethodLinksMean ScoreSTD ScoreMin ScoreMax ScoreNFQ2025.0929.7551.473.7323.68SAC2025.092.240.441.453.31DQN2025.090.750.170.451.07DDQN2025.090.390.10.140.65BCQ2025.090.320.140.080.67CQL2025.09-0.390.31-1.130.13