{"id":"W19532835","doi":"10.1609/aiide.v4i1.18667","title":"Agent Learning Using Action-Dependent Learning Rates in Computer Role-Playing Games","year":2008,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Action (physics); Computer science; Reinforcement learning; Scripting language; Artificial intelligence; Error-driven learning; Learning effect; Human–computer interaction","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"],"consensus_categories":[],"category_scores_codex":[0.0002450825,0.000301759,0.000313314,0.0002461885,0.00033052,0.0005542227,0.0007105392,0.00007034087,0.00002273528],"category_scores_gemma":[0.0002261425,0.00024609,0.0001155197,0.0002965952,0.000188574,0.001548184,0.0006314433,0.0006674526,0.00002560079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002151956,"about_ca_system_score_gemma":0.00005276229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000054329,"about_ca_topic_score_gemma":0.000002230351,"domain_scores_codex":[0.9978591,0.00003796071,0.0006328596,0.0005420245,0.0005264468,0.0004016706],"domain_scores_gemma":[0.9988247,0.0001581241,0.0005041723,0.0001456384,0.0002767342,0.00009063361],"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":[0.0004911857,0.0007485767,0.1268248,0.0001206475,0.0002144132,0.00002196887,0.03068809,0.514202,0.04556563,0.04632843,0.00001946291,0.2347748],"study_design_scores_gemma":[0.00009142872,0.0005229782,0.001199293,0.0005025052,0.000007553123,0.00003793596,0.003974015,0.9216982,0.07024205,0.001363506,0.00006499197,0.0002955541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7933535,0.00001531512,0.203182,0.0002255122,0.0002780234,0.0003118849,7.751946e-7,0.0000527279,0.002580271],"genre_scores_gemma":[0.9985801,0.00009069919,0.0008819069,0.00008419721,0.00004648792,0.00001523533,0.000001348651,0.00001609753,0.0002839167],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4074962,"threshold_uncertainty_score":0.9999991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07247847678986213,"score_gpt":0.3010187550703153,"score_spread":0.2285402782804532,"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."}}