{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001236572,0.0001735953,0.0001209949,0.0002608436,0.0004976129,0.0002228453,0.0003406452,0.00005351339,0.002148012],"category_scores_gemma":[0.001210589,0.0001503625,0.00005026264,0.0002583821,0.000317923,0.0004568801,0.0001086641,0.0005209415,0.0004912233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007622087,"about_ca_system_score_gemma":0.00008275975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006030314,"about_ca_topic_score_gemma":0.00002180303,"domain_scores_codex":[0.9981095,0.0001914469,0.0002715939,0.0005381445,0.0006620265,0.0002273507],"domain_scores_gemma":[0.9984136,0.0006824746,0.0002350675,0.0001686916,0.0004195604,0.00008055429],"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":[0.0006036435,0.0002781083,0.03153994,0.000007704701,0.0001600999,0.00006581431,0.01160473,0.4860498,0.07625679,0.3830659,0.0008816113,0.009485914],"study_design_scores_gemma":[0.001473404,0.001937728,0.01413643,0.0003354794,0.00002690801,0.0001144534,0.003707639,0.8689534,0.09104052,0.00279781,0.01482489,0.0006513358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6782024,0.000003020778,0.05562949,0.003538297,0.0006671176,0.0002597945,0.00000297171,0.0002790046,0.261418],"genre_scores_gemma":[0.9869832,0.00001049723,0.0007774616,0.0003719701,0.0003305957,0.00004254809,0.00003826415,0.00001893238,0.01142649],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3829036,"threshold_uncertainty_score":0.9987642,"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."}}