{"id":"W2907502844","doi":"","title":"Deep reinforcement learning with relational inductive biases","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":136,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inductive bias; Statistical relational learning; Reinforcement learning; Computer science; Artificial intelligence; Inductive logic programming; Machine learning; Relational database; Multi-task learning; Data mining; 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":[0.001721811,0.0006083814,0.0007862602,0.0003431814,0.0003535918,0.0009697622,0.001477694,0.001238002,0.004598733],"category_scores_gemma":[0.008113764,0.0004696109,0.0004494165,0.0004163083,0.0009528093,0.002145711,0.00220247,0.002379697,0.0005121077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008325787,"about_ca_system_score_gemma":0.0009268863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00171607,"about_ca_topic_score_gemma":0.002743534,"domain_scores_codex":[0.9994079,0.0002456826,0.00003326364,0.0001350837,0.0001065739,0.00007151012],"domain_scores_gemma":[0.9969313,0.002001027,0.0001800405,0.0003796541,0.000363558,0.0001444119],"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":[0.0003237913,0.0003078596,0.002323459,0.0001689553,0.0001377581,0.0001446955,0.0001940974,0.6110065,0.006846521,0.08573563,0.003585159,0.2892256],"study_design_scores_gemma":[0.0000135628,0.00003575595,0.00007934893,0.0000102685,0.00001085841,0.00001434966,0.000006942278,0.9709333,0.001059902,0.02740816,0.0004226304,0.000004977949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06718229,0.0004852491,0.9260755,0.001097812,0.0001655655,0.00006243877,0.0001120149,0.0006840636,0.004134982],"genre_scores_gemma":[0.8996946,0.0001930309,0.09483505,0.0002798404,0.00007945579,0.00009275026,0.0001285353,0.00008494221,0.004611741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004598733,"threshold_uncertainty_score":0.01538432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1159802418290208,"score_gpt":0.3604810611844719,"score_spread":0.244500819355451,"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."}}