{"id":"W4415428281","doi":"10.3233/faia251077","title":"DmC: Nearest Neighbor Guidance Diffusion Model for Offline Cross-Domain Reinforcement Learning","year":2025,"lang":"","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Overfitting; Reinforcement learning; Domain (mathematical analysis); Key (lock); Artificial neural network; Sample (material); k-nearest neighbors algorithm","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002449865,0.001238222,0.001827795,0.0006378717,0.0005225024,0.001258017,0.002574298,0.001680651,0.002661891],"category_scores_gemma":[0.007900404,0.0005818434,0.0006183102,0.0005964735,0.001451988,0.001695496,0.002026485,0.002910152,0.0005755633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001553721,"about_ca_system_score_gemma":0.002028516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01003504,"about_ca_topic_score_gemma":0.008061335,"domain_scores_codex":[0.9989337,0.0003199945,0.00005448154,0.000307166,0.0002523221,0.0001322195],"domain_scores_gemma":[0.9968406,0.00177136,0.0003429786,0.0002656528,0.0005733374,0.0002060899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001021007,0.00008968438,0.0008540911,0.00006776677,0.00003766968,0.00007337089,0.0000740647,0.9516385,0.0009806553,0.008955542,0.001494117,0.0356323],"study_design_scores_gemma":[0.000005381643,0.00001397788,0.00003934279,0.000003516309,0.000002147104,0.000005534437,0.000002645907,0.9982536,0.0001293313,0.001366423,0.0001744928,0.000003573577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01768327,0.00049769,0.9780008,0.0003425663,0.00006365251,0.0000919353,0.00008827195,0.0005885178,0.002643237],"genre_scores_gemma":[0.8820152,0.0002724709,0.1115583,0.0004537116,0.00005194532,0.0003646196,0.000266171,0.0001375239,0.004880091],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01003504,"threshold_uncertainty_score":0.01995325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04380986476356294,"score_gpt":0.3078464961854975,"score_spread":0.2640366314219346,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}