{"id":"W2155110786","doi":"10.1109/icsmc.2007.4414135","title":"An improved immune Q-learning algorithm","year":2007,"lang":"en","type":"article","venue":"","topic":"Artificial Immune Systems Applications","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Reinforcement learning; Computer science; Task (project management); Q-learning; Artificial intelligence; Set (abstract data type); Key (lock); Machine learning; Action selection; Action (physics); Artificial immune system; Instance-based learning; Algorithm; Active learning (machine learning); Engineering; Perception","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":[],"consensus_categories":[],"category_scores_codex":[0.0002897661,0.00008277293,0.00008889191,0.00005310667,0.00008463583,0.00002547153,0.0001112308,0.00005374446,0.0001016921],"category_scores_gemma":[0.000006139408,0.00008504756,0.00002774563,0.0001506995,0.00001333744,0.0001202402,0.00001171801,0.0001328905,0.00023205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000352549,"about_ca_system_score_gemma":0.000004096344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001675609,"about_ca_topic_score_gemma":0.00004029783,"domain_scores_codex":[0.9993852,0.000007667561,0.0002340199,0.00009758434,0.0000582349,0.0002173311],"domain_scores_gemma":[0.9996247,0.00002144868,0.00001764712,0.0002456986,0.00002969419,0.00006078262],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[9.701783e-7,0.00001759342,0.00007993823,0.000005944136,0.00001604408,0.000001148392,0.0002902514,0.001477198,0.735486,0.0007671917,0.00008414203,0.2617736],"study_design_scores_gemma":[0.0001566604,0.00004628027,0.005478986,0.000005710382,0.000007907366,0.000008800748,0.001192477,0.7478438,0.2075433,0.0001037301,0.03729389,0.0003185059],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04368176,0.0001363452,0.925668,0.0000106007,0.0001951489,0.0001709904,9.443855e-7,0.001299543,0.02883665],"genre_scores_gemma":[0.9794232,0.000003320832,0.01962982,0.000007752014,0.0001144141,0.00001479506,0.00001141615,0.00003456086,0.0007606784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9357415,"threshold_uncertainty_score":0.3468139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005216335561126262,"score_gpt":0.232556334052529,"score_spread":0.2273399984914027,"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."}}