{"id":"W41346994","doi":"","title":"Bootstrapping the Learning Process for the Semi-automated Design of a Challenging Game AI","year":2004,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Bootstrapping (finance); Artificial intelligence; Process (computing); Key (lock); Game design; Representation (politics); Decomposition; Control (management); Machine learning; Human–computer interaction; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006362273,0.0003448081,0.0003612437,0.0001583664,0.0007068313,0.0006491718,0.003897685,0.0002227652,0.000008767521],"category_scores_gemma":[0.002021435,0.0002599267,0.000223163,0.0005270265,0.0002623687,0.0002182518,0.001450606,0.001084552,0.000006215215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001232359,"about_ca_system_score_gemma":0.000595457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001437844,"about_ca_topic_score_gemma":0.00001736925,"domain_scores_codex":[0.9949536,0.002641208,0.0006647852,0.000660708,0.0006123855,0.0004672606],"domain_scores_gemma":[0.9908023,0.003933421,0.0009931844,0.002220994,0.001970473,0.00007964313],"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":[0.000003842567,0.00004800407,0.00005017648,0.0002167147,0.00008716922,6.905511e-7,0.01112607,0.9700755,0.0002317567,0.01737237,0.00002934515,0.000758348],"study_design_scores_gemma":[0.0003152186,0.000001080868,0.0001957435,0.001741939,0.00004137192,0.000006586629,0.0002182048,0.9889496,0.005799581,0.001681809,0.0007891479,0.0002597383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006945257,0.0008994591,0.9860305,0.008928919,0.0002107045,0.001234154,0.000002841617,0.0006831926,0.001315655],"genre_scores_gemma":[0.9950072,0.0003773282,0.003245108,0.0001112311,0.00002170748,0.0002114649,0.00003241849,0.00004277841,0.0009508351],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9943126,"threshold_uncertainty_score":0.9999853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03322517527403423,"score_gpt":0.2744859141496011,"score_spread":0.2412607388755669,"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."}}