{"id":"W2946045694","doi":"10.24963/ijcai.2019/85","title":"A Regularized Opponent Model with Maximum Entropy Objective","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Principle of maximum entropy; Computer science; Inference; Binary number; Mathematical optimization; Probabilistic logic; Iterated function; Random variable; Artificial intelligence; Algorithm; Mathematics","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":[0.000306438,0.0004855728,0.0005479839,0.0002126345,0.00008412526,0.0005313338,0.002280762,0.0003073368,0.00003497357],"category_scores_gemma":[0.00003174798,0.0003777966,0.0001732031,0.0001787556,0.00006565231,0.0002829157,0.003577001,0.0009466971,0.0002242019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002957916,"about_ca_system_score_gemma":0.0007367008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005559376,"about_ca_topic_score_gemma":0.000001717407,"domain_scores_codex":[0.9969323,0.0000985715,0.000397346,0.001115566,0.0009172003,0.0005390546],"domain_scores_gemma":[0.9966565,0.0000713726,0.000392044,0.002472747,0.0002592389,0.0001480448],"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":[0.00003298082,0.00002698414,0.0000782222,0.00006085698,0.0001261123,0.00001268832,0.0004870593,0.9513723,0.0001281343,0.04700194,0.0004390023,0.0002337039],"study_design_scores_gemma":[0.0007270946,0.0001401755,0.00007854938,0.0001078401,0.00003184364,0.00001031462,0.00002008912,0.9892235,0.0004671588,0.008448056,0.0002152179,0.0005301042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005965491,0.00002043674,0.9731176,0.0008531034,0.0005917531,0.001009466,0.000002611729,0.0005083341,0.02330014],"genre_scores_gemma":[0.1766231,0.00003394909,0.7893158,0.0005518486,0.00006609713,0.00009031645,0.00003902454,0.00005531308,0.03322454],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1838018,"threshold_uncertainty_score":0.9998674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01899547368216535,"score_gpt":0.2364777973377845,"score_spread":0.2174823236556192,"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."}}