{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002428471,0.0008588978,0.001078005,0.0008579727,0.000414312,0.001287632,0.00227871,0.001290261,0.002763296],"category_scores_gemma":[0.008472736,0.0005115501,0.0008857846,0.0007561647,0.001944476,0.003619381,0.002086879,0.002087952,0.0005318447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008840165,"about_ca_system_score_gemma":0.001313609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002829548,"about_ca_topic_score_gemma":0.00311911,"domain_scores_codex":[0.9991831,0.0002892936,0.0000372786,0.0001774134,0.0002064946,0.0001063071],"domain_scores_gemma":[0.9964787,0.002134332,0.0003118966,0.000567302,0.0003464998,0.0001612048],"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":[0.0001050612,0.00009555217,0.0009256602,0.0001165699,0.00004968118,0.0001306291,0.000164352,0.7919825,0.002303568,0.1071413,0.001206356,0.09577879],"study_design_scores_gemma":[0.00001229281,0.00003600682,0.00003983354,0.000009055347,0.000006711494,0.00001592642,0.000005441035,0.9673041,0.0006340982,0.03145768,0.0004731134,0.000005773328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01746672,0.0002085562,0.979624,0.0002177228,0.00002878205,0.00003038405,0.00003904434,0.0007091186,0.001675668],"genre_scores_gemma":[0.6874775,0.0003423018,0.30895,0.000211961,0.00007674097,0.0001819981,0.0001628312,0.0001662852,0.002430397],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002829548,"threshold_uncertainty_score":0.01284313,"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."}}