{"id":"W2964190622","doi":"","title":"Eigenoption Discovery through the Deep Successor Representation","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Successor cardinal; Representation (politics); Feature learning; Exploit; Deep learning; Leverage (statistics); ENCODE; Machine learning; Intuition; Cognitive science; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000146205,0.0001065218,0.00009080571,0.0000357292,0.00101476,0.0006633807,0.001978626,0.00004973348,0.00001286109],"category_scores_gemma":[0.00009331385,0.00009039487,0.00007469303,0.0001856523,0.0001538886,0.003736949,0.0005512228,0.0001403309,0.000119567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006823154,"about_ca_system_score_gemma":0.00002974119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002227341,"about_ca_topic_score_gemma":0.00004390253,"domain_scores_codex":[0.9991155,0.00007410508,0.0001056456,0.0003865557,0.0001014857,0.0002167659],"domain_scores_gemma":[0.9979978,0.00008634842,0.0002579065,0.001553199,0.00006831507,0.00003644532],"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":[0.000007085392,0.000008833543,0.008886182,0.000003031689,0.00001683905,0.00002645443,0.0002989612,0.7025069,0.00004779545,0.2878585,0.00006898613,0.0002704275],"study_design_scores_gemma":[0.0003574326,0.00004223674,0.02843072,0.00001095377,0.00002318593,0.000003334382,0.0001611659,0.9592267,0.0003782186,0.01014098,0.001052645,0.000172491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06979012,0.000007200205,0.917608,0.000422138,0.0003595753,0.0001313375,3.49221e-7,0.0000807578,0.01160055],"genre_scores_gemma":[0.9923828,0.00006894466,0.001226807,0.00009892302,0.00005858966,4.112458e-7,0.000002481934,0.000006323544,0.006154669],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9225928,"threshold_uncertainty_score":0.7804812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09020491085728016,"score_gpt":0.2271458275076368,"score_spread":0.1369409166503566,"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."}}