{"id":"W2794958591","doi":"10.1109/iros.2018.8594242","title":"Accelerating Learning in Constructive Predictive Frameworks with the Successor Representation","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Constructive; Successor cardinal; Reinforcement learning; Interdependence; Representation (politics); Machine learning; Process (computing); Task (project management); Robot; Grid; Field (mathematics); Robotics; 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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0006161292,0.0003100227,0.0003136747,0.0001802283,0.000283188,0.0009361591,0.001578736,0.0004667176,0.00004646548],"category_scores_gemma":[0.000377029,0.0002068462,0.00006093047,0.0005211548,0.00029062,0.0005481516,0.002125909,0.00365495,0.00001868978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001570912,"about_ca_system_score_gemma":0.0002708789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001785208,"about_ca_topic_score_gemma":0.00003988631,"domain_scores_codex":[0.9973642,0.000383889,0.0004036519,0.0008371784,0.0006294978,0.0003816219],"domain_scores_gemma":[0.9974059,0.000670151,0.0005956734,0.0009136249,0.0003603487,0.00005434089],"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":[0.00001868911,0.000007316689,0.0287441,0.00001742241,0.00006054303,0.000008101554,0.004285806,0.9603757,0.000004729995,0.004795572,0.0001531907,0.001528815],"study_design_scores_gemma":[0.0002598034,0.0001634184,0.01290567,0.0002599724,0.00001587942,0.000008996429,0.001055579,0.9834116,0.000233842,0.001343864,0.00006065232,0.0002807081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02571417,0.00001734674,0.9496009,0.001274098,0.0004210315,0.0007262895,5.057561e-7,0.000303959,0.0219417],"genre_scores_gemma":[0.894711,0.0000127674,0.1039576,0.0002429267,0.0001950568,0.0001116817,0.00001363716,0.00002330059,0.000732023],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8689969,"threshold_uncertainty_score":0.9986436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02404667894933301,"score_gpt":0.2852600510444348,"score_spread":0.2612133720951018,"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."}}