{"id":"W2785948534","doi":"","title":"NerveNet: Learning Structured Policy with Graph Neural Networks","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":155,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Concatenation (mathematics); Computer science; Transfer of learning; Artificial intelligence; Graph; Benchmarking; Machine learning; Artificial neural network; Control (management); Theoretical computer 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":[0.0008886644,0.0007510662,0.0007149902,0.0005093642,0.0002766699,0.0005849849,0.001191748,0.001106656,0.002560674],"category_scores_gemma":[0.003573085,0.0003750398,0.0004034023,0.0004310197,0.0008421114,0.001250592,0.0008722362,0.001443749,0.000490779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008313048,"about_ca_system_score_gemma":0.001309435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005436162,"about_ca_topic_score_gemma":0.00684453,"domain_scores_codex":[0.9997265,0.00008783876,0.00001291296,0.00006914877,0.00006718761,0.00003647517],"domain_scores_gemma":[0.9990047,0.0005756516,0.0001035785,0.0001210264,0.0001269472,0.00006810696],"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":[0.00004468929,0.00004654371,0.0003578648,0.0000351798,0.00002190349,0.0000345557,0.00001687485,0.9576289,0.0005887345,0.007076573,0.001427115,0.03272104],"study_design_scores_gemma":[0.000004507508,0.00001430572,0.00002174723,0.000002453028,0.000001588965,0.000004024357,0.000001229614,0.9956046,0.0002177937,0.003896583,0.0002294372,0.000001686151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03274063,0.0003472783,0.9600867,0.0004818095,0.0001686792,0.00007158482,0.0001935592,0.002493299,0.003416448],"genre_scores_gemma":[0.7861734,0.0003007497,0.2080812,0.0004578753,0.00007610657,0.0002276962,0.0004892196,0.0002507826,0.003942954],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005436162,"threshold_uncertainty_score":0.010809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03155445305249521,"score_gpt":0.3241901345896976,"score_spread":0.2926356815372024,"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."}}