{"id":"W3132477017","doi":"","title":"Non-Linear Rewards For Successor Features","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Successor cardinal; Computer science; Reinforcement learning; Artificial intelligence; Machine learning; Feature (linguistics); Function (biology); Term (time); Mathematics","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":[0.001574061,0.0008044834,0.0009573897,0.0004992675,0.0003740651,0.0008226936,0.001318921,0.0008864027,0.002666224],"category_scores_gemma":[0.006380513,0.0003924952,0.0006139126,0.0003498403,0.001481437,0.002246963,0.001334367,0.00201323,0.0003618113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001118371,"about_ca_system_score_gemma":0.001125502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001925143,"about_ca_topic_score_gemma":0.002406443,"domain_scores_codex":[0.999283,0.0002361726,0.0000378381,0.0001666092,0.0001814565,0.00009492833],"domain_scores_gemma":[0.9971452,0.001791255,0.0003363045,0.000328666,0.0002391559,0.000159437],"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":[0.0002183548,0.0001400331,0.002014035,0.00008039958,0.00003816036,0.0001501834,0.00009769238,0.8469123,0.002456147,0.07103092,0.001124333,0.07573744],"study_design_scores_gemma":[0.000007444049,0.00004169857,0.0001738727,0.000005942037,0.000004283601,0.00002111742,0.000003393134,0.9853787,0.0003770664,0.01376009,0.0002192089,0.000007116362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04928717,0.0001682872,0.9477547,0.0002688114,0.00003336848,0.00003462418,0.00006045918,0.000431771,0.001960858],"genre_scores_gemma":[0.9380307,0.00009015498,0.05868898,0.00007816951,0.00002661294,0.00008857242,0.00007656113,0.00006151203,0.002858683],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002666224,"threshold_uncertainty_score":0.008919418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01908450848725854,"score_gpt":0.2887595636198263,"score_spread":0.2696750551325677,"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."}}