{"id":"W2906796853","doi":"10.1109/ijcnn52387.2021.9533459","title":"Dynamic Planning Networks","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Ontario Centres of Excellence","keywords":"Traverse; Computer science; Generalization; Reinforcement learning; Action (physics); Artificial intelligence; Construct (python library); State (computer science); Architecture; Machine learning; Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002140714,0.0002329517,0.0002572378,0.00008973411,0.00007873028,0.0009237582,0.001686051,0.0002710297,0.00006212066],"category_scores_gemma":[0.00003693172,0.0002336453,0.0001232561,0.0001732818,0.00002119844,0.0001698153,0.004601176,0.0009740808,0.00002726869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009059213,"about_ca_system_score_gemma":0.0001488184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000148798,"about_ca_topic_score_gemma":0.000001675257,"domain_scores_codex":[0.9983841,0.00006116359,0.0002960018,0.0005964329,0.0003192173,0.0003430407],"domain_scores_gemma":[0.9982913,0.00008277066,0.000171229,0.001290618,0.00008280708,0.00008133069],"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":[2.930754e-7,0.000004213245,0.0002280904,0.00002268811,0.00003045521,0.00005245763,0.0001976731,0.9956477,0.000002323569,0.001840921,0.0004360213,0.001537121],"study_design_scores_gemma":[0.00005544358,0.00001157101,0.0007296508,0.0001529481,0.000006462481,0.000008419081,0.00002556138,0.9981177,0.000006494522,0.0001298969,0.0004905688,0.0002652136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000432545,0.0004337193,0.9779558,0.0002408999,0.002287087,0.0001228841,1.023821e-7,0.0004912865,0.01803565],"genre_scores_gemma":[0.576041,0.00007034675,0.4169029,0.000615219,0.00007938788,0.00001574664,0.00005676099,0.00002476479,0.006193839],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5756085,"threshold_uncertainty_score":0.9527779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01973673017005091,"score_gpt":0.2760966982052132,"score_spread":0.2563599680351623,"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."}}