{"id":"W2794468939","doi":"","title":"Rewards Structure in Games: Learning a Compact Representation for Action Space.","year":2017,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Computer science; Representation (politics); Space (punctuation); Action (physics); Theoretical computer science; Artificial intelligence; Human–computer interaction; Physics","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":[0.0003667894,0.0001321601,0.0001460655,0.000246616,0.0005445185,0.0007102915,0.0005042879,0.00009784877,0.0001422384],"category_scores_gemma":[0.001272926,0.0001359728,0.00006202344,0.0001429028,0.00006858222,0.0009839771,0.00003920547,0.0002828047,0.00008596405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001329849,"about_ca_system_score_gemma":0.0001685759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008253501,"about_ca_topic_score_gemma":0.0003187089,"domain_scores_codex":[0.9985437,0.00007883371,0.0003006876,0.0004214832,0.000455577,0.0001996775],"domain_scores_gemma":[0.9986047,0.0002234874,0.0002982667,0.0002675614,0.0005488176,0.00005720434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008027827,0.00009382722,0.0003354443,0.00001323399,0.00001117302,0.000003143905,0.000576412,0.005304669,0.009154926,0.6526434,0.0002408862,0.3315426],"study_design_scores_gemma":[0.0001050752,0.0001586542,0.008612138,0.00008061733,0.00000339077,0.000004022686,0.0002972969,0.3990624,0.09490294,0.4954887,0.001048497,0.0002362526],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1468309,0.000009797305,0.8268301,0.008314607,0.001347908,0.0007255656,0.00003258515,0.0001795763,0.01572896],"genre_scores_gemma":[0.9976469,0.00001922227,0.001697516,0.0001233574,0.0001740036,0.00002265136,0.00002934552,0.000006891544,0.0002801238],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.850816,"threshold_uncertainty_score":0.6849357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2837771291093321,"score_gpt":0.4380129574277635,"score_spread":0.1542358283184314,"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."}}