{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001010052,0.0008785556,0.0009453405,0.0007224206,0.001523418,0.0008901095,0.001733338,0.0006714595,0.00005427722],"category_scores_gemma":[0.0002161904,0.001018749,0.0003233993,0.000532218,0.0008653214,0.0005177899,0.0009213785,0.001224457,0.00005334037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003663328,"about_ca_system_score_gemma":0.0004224591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003500814,"about_ca_topic_score_gemma":0.00002771883,"domain_scores_codex":[0.994057,0.00005658206,0.002445668,0.001787869,0.0006595961,0.00099327],"domain_scores_gemma":[0.9964509,0.0003478484,0.001030236,0.001323043,0.0005660302,0.0002819594],"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":[0.00006053216,0.0000408219,0.0002106216,0.0001350781,0.00003387992,0.00000118401,0.0004064323,0.5382848,0.00003090427,0.375927,0.0002364169,0.08463238],"study_design_scores_gemma":[0.0001298597,0.0001730565,0.000013992,0.0004757703,0.0000545056,0.000001334234,0.0001804493,0.8213257,0.000198747,0.1200484,0.05665374,0.0007444666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002304927,0.0009732836,0.9793102,0.0006987151,0.0008592725,0.003654906,0.00003530272,0.0001174004,0.01432786],"genre_scores_gemma":[0.1173574,0.00924017,0.5697348,0.001052672,0.001175072,0.003198851,0.0005607549,0.0002276197,0.2974527],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4095755,"threshold_uncertainty_score":0.9997765,"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."}}