{"id":"W2962985403","doi":"","title":"Universal Successor Representations for Transfer Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Initialization; Successor cardinal; Artificial intelligence; Set (abstract data type); Transfer of learning; Focus (optics); Function (biology); Machine learning; Reinforcement; Value (mathematics); Mathematics; Programming language","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":[0.0003860111,0.000255444,0.0002055387,0.0004556193,0.0008462836,0.0006392947,0.001310609,0.0001018261,0.0008189778],"category_scores_gemma":[0.0008723523,0.0002766501,0.0001697655,0.0004440285,0.0002053109,0.001020613,0.0002097679,0.0005105122,0.0003443466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001619587,"about_ca_system_score_gemma":0.0001924054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001004868,"about_ca_topic_score_gemma":0.00001634067,"domain_scores_codex":[0.9973381,0.0001738092,0.0005313139,0.0007311915,0.0007895802,0.0004359924],"domain_scores_gemma":[0.9974065,0.0005294795,0.0002116844,0.0005177787,0.001185457,0.0001490976],"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":[0.00006226524,0.00003998314,0.002302328,0.000006864697,0.0001175348,0.000005217757,0.003105864,0.5506719,0.001464914,0.4392788,0.000797132,0.002147251],"study_design_scores_gemma":[0.001153241,0.000639581,0.001724971,0.0000615016,0.00002424736,0.000009384714,0.00101235,0.9670334,0.002136154,0.001623324,0.02423479,0.000347023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003632814,0.00000290474,0.8863748,0.004339714,0.0009543651,0.000452735,0.000003317493,0.0003920005,0.1038474],"genre_scores_gemma":[0.9568276,0.00003192067,0.008169136,0.0002300861,0.0003406528,0.000132419,0.0001592305,0.00002894489,0.03408001],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9531948,"threshold_uncertainty_score":0.9999686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05728557116336094,"score_gpt":0.3472003823606163,"score_spread":0.2899148111972554,"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."}}