{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001315437,0.0005586618,0.0008535112,0.0005763117,0.0005076707,0.001227345,0.00109061,0.001262623,0.002554999],"category_scores_gemma":[0.004860844,0.0004704713,0.0006234132,0.0004184543,0.001651598,0.002590801,0.001830552,0.001806996,0.0003164635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008739146,"about_ca_system_score_gemma":0.001030671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001239397,"about_ca_topic_score_gemma":0.001842195,"domain_scores_codex":[0.9996081,0.0001603362,0.00002094613,0.00008859988,0.00006500851,0.00005689519],"domain_scores_gemma":[0.9985231,0.0009887225,0.0001540882,0.0001443761,0.00009100555,0.0000987835],"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":[0.0002193889,0.0001089671,0.002084841,0.0001071029,0.00005139512,0.0001485068,0.0002530094,0.6871555,0.003746882,0.1869107,0.002468025,0.1167458],"study_design_scores_gemma":[0.00001289232,0.00002841862,0.00007654836,0.00001293081,0.000004747326,0.00002149003,0.00001384096,0.9380199,0.0006695645,0.0607408,0.0003903285,0.000008376192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06040246,0.0002431143,0.9348667,0.0005499081,0.00003256155,0.00005124395,0.00007901413,0.0004158595,0.003359196],"genre_scores_gemma":[0.8243931,0.0001336637,0.171774,0.0001757384,0.00001758075,0.0001349191,0.0001061271,0.00009134828,0.003173515],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002554999,"threshold_uncertainty_score":0.008547366,"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."}}