{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000199191,0.0002447878,0.0001743839,0.0004763326,0.000558124,0.000728846,0.001190451,0.00008664132,0.0003598428],"category_scores_gemma":[0.0004420097,0.0002229986,0.00008436919,0.0007366007,0.0002303373,0.0006319091,0.0002624069,0.0007806949,0.00009284297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009306435,"about_ca_system_score_gemma":0.0001392899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001766024,"about_ca_topic_score_gemma":0.00003002943,"domain_scores_codex":[0.997707,0.0002255176,0.0003400013,0.0005909106,0.0007317698,0.0004048015],"domain_scores_gemma":[0.998197,0.0002011452,0.0003335754,0.000456176,0.0006725632,0.0001395134],"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":[0.00003055944,0.000014665,0.01517284,0.000001731791,0.00006474299,0.00001168991,0.0009398565,0.8629991,0.0001576712,0.1134301,0.0001022769,0.00707478],"study_design_scores_gemma":[0.0004680232,0.0005168562,0.01805655,0.00004060552,0.000007939104,0.00003467915,0.0002290695,0.9776757,0.0001279989,0.0009978125,0.001591119,0.0002536277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01786044,0.000006323301,0.9243043,0.003526348,0.0006315684,0.0001796455,0.000001010131,0.0004409599,0.0530494],"genre_scores_gemma":[0.9871295,0.00001581982,0.005333061,0.0003050997,0.0005668472,0.00002630485,0.0000519121,0.00002635578,0.006545114],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.969269,"threshold_uncertainty_score":0.9093618,"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."}}