{"id":"W3034833014","doi":"","title":"OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Ground; Reinforcement; Artificial intelligence; Cognitive psychology; Human–computer interaction; Cognitive science; Psychology; Engineering; Social psychology; Electrical engineering","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":[0.000619512,0.0003127404,0.0002636769,0.0004825984,0.0003207404,0.0006228896,0.001349751,0.00008738273,0.0004587475],"category_scores_gemma":[0.001250804,0.0003267371,0.0001152603,0.0004164879,0.00006786067,0.0007161106,0.0006254051,0.001609011,0.0004605243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002576937,"about_ca_system_score_gemma":0.0001335596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002685733,"about_ca_topic_score_gemma":0.00001667681,"domain_scores_codex":[0.9970029,0.0004487997,0.000606654,0.0006194619,0.0008693262,0.0004528459],"domain_scores_gemma":[0.9988338,0.0002366707,0.0003139128,0.0002480605,0.0001651907,0.0002023989],"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":[0.00008918352,0.0000338953,0.03874375,0.000008929851,0.00002898199,0.00008371561,0.003077358,0.845041,0.001001793,0.1089869,0.00001038328,0.002894064],"study_design_scores_gemma":[0.0009758543,0.0005449527,0.00797199,0.000120191,0.000005837497,0.00001633863,0.000418385,0.9857543,0.0001348113,0.0001415477,0.003576506,0.0003392499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04271102,0.00003438758,0.9384139,0.007590912,0.0004968829,0.0002836643,0.000001386864,0.0004155662,0.01005234],"genre_scores_gemma":[0.981647,0.0001169955,0.01156042,0.0008189139,0.00006977585,0.00003584298,0.00006433506,0.0000272576,0.005659487],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9389359,"threshold_uncertainty_score":0.9999185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1289016132082067,"score_gpt":0.3483189519549212,"score_spread":0.2194173387467145,"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."}}