{"id":"W4415688799","doi":"10.1007/978-3-032-04339-9_15","title":"Enhancing Off-Policy Method SAC with KAN for Continuous Reinforcement Learning","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"","keywords":"Reinforcement learning; Embedding; Architecture; Reinforcement; Artificial neural network","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":[0.001069551,0.0007107896,0.0008546647,0.0004625522,0.0003983074,0.0008650169,0.001206958,0.0009567646,0.007544687],"category_scores_gemma":[0.002554514,0.0002698355,0.0004701387,0.0003120486,0.0008241628,0.001055175,0.0016047,0.001873022,0.001462569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006032768,"about_ca_system_score_gemma":0.001275688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001700231,"about_ca_topic_score_gemma":0.001923217,"domain_scores_codex":[0.9994934,0.0001424526,0.00002400669,0.00009898725,0.0001836986,0.00005751118],"domain_scores_gemma":[0.9989667,0.0004844804,0.00006310608,0.0001673369,0.0002332647,0.00008513362],"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":[0.0005029992,0.0003259466,0.0007405972,0.0002857997,0.0000768232,0.0001364799,0.0001328626,0.4909021,0.01636599,0.05842379,0.005674529,0.4264322],"study_design_scores_gemma":[0.00001576657,0.00007306655,0.00006942573,0.000006965935,0.00000711034,0.0000361405,0.000005806041,0.9907699,0.00136429,0.006074322,0.001571191,0.000006046086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007394944,0.0001790956,0.9858968,0.00008085839,0.0001446042,0.00004018619,0.00001721149,0.0008278581,0.005418452],"genre_scores_gemma":[0.5891466,0.0002418928,0.3960967,0.0002268608,0.0001410227,0.0001781647,0.00007991992,0.0003971508,0.01349176],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007544687,"threshold_uncertainty_score":0.02523953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02445174135414655,"score_gpt":0.3154284189345152,"score_spread":0.2909766775803686,"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."}}