{"id":"W4391157052","doi":"","title":"Using Confounded Data in Latent Model-Based Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ubisoft (Canada); Montfort Hospital; Minnow Environmental (Canada)","funders":"Canada First Research Excellence Fund; Canada Excellence Research Chairs, Government of Canada","keywords":"Reinforcement learning; Computer science; Reinforcement; Latent inhibition; Artificial intelligence; Cognitive psychology; Machine learning; Psychology; Statistics; Social psychology; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00632547,0.0002106091,0.0002245336,0.0003612063,0.0003482745,0.0004657088,0.002699893,0.00009846928,0.00002785953],"category_scores_gemma":[0.001298149,0.000234714,0.00006276241,0.001287168,0.0001054258,0.0006019183,0.001840144,0.0003962555,0.00009735081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001707986,"about_ca_system_score_gemma":0.0003499188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004132929,"about_ca_topic_score_gemma":0.0001575918,"domain_scores_codex":[0.9960001,0.001679325,0.0005297111,0.0006724807,0.0006108321,0.0005075127],"domain_scores_gemma":[0.995411,0.0008303006,0.0002992255,0.002753653,0.000572909,0.0001329109],"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":[0.000002733753,0.00003741397,0.001989589,0.00002448442,0.00001065108,0.000006381752,0.001672081,0.9525897,0.000991044,0.03996837,0.00009593351,0.002611628],"study_design_scores_gemma":[0.0005704779,5.03907e-7,0.0006297015,0.000313151,0.00000668475,0.000002107146,0.00003254751,0.993592,0.002712982,0.0003570626,0.001544474,0.0002383261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01231068,0.0000347036,0.9752958,0.002671332,0.0001071738,0.000252816,0.000001702685,0.0004693129,0.008856501],"genre_scores_gemma":[0.8784171,0.00005263145,0.1161317,0.0001286869,0.000006653086,0.00001244797,0.0002482279,0.000025706,0.004976844],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8661064,"threshold_uncertainty_score":0.9571358,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06579403889571468,"score_gpt":0.2846853523510118,"score_spread":0.2188913134552972,"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."}}