{"id":"W4320342078","doi":"10.48550/arxiv.2302.00237","title":"Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Waterloo","keywords":"Hamilton–Jacobi–Bellman equation; Reinforcement learning; Bellman equation; Artificial neural network; Bridging (networking); Computer science; Mathematical optimization; Optimal control; Mathematics; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003422039,0.0007476312,0.0005858816,0.0005948488,0.0006004813,0.0006009864,0.002367871,0.0003769774,0.00001577926],"category_scores_gemma":[0.00008701281,0.0008217042,0.0002706193,0.001919793,0.0002118514,0.001112109,0.002716326,0.001856044,0.00006663294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00085559,"about_ca_system_score_gemma":0.0007343714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002982077,"about_ca_topic_score_gemma":0.00001580158,"domain_scores_codex":[0.9963378,0.0001735997,0.0005239412,0.001444061,0.0004073876,0.001113258],"domain_scores_gemma":[0.9966499,0.0001537814,0.0009553347,0.001572757,0.0003500271,0.0003182435],"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":[0.00005605044,0.00002410959,0.002360606,0.0001261865,0.0001727476,0.0001571737,0.0005955938,0.9820542,0.000001152058,0.01393126,0.0001507339,0.0003701281],"study_design_scores_gemma":[0.0009276087,0.0002933067,0.0002430601,0.0002285749,0.00008825854,0.000007713939,0.00006952589,0.9969379,0.00002111355,0.0001393101,0.0001592118,0.0008843797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003436289,0.000008505294,0.9910418,0.0002040111,0.0005643163,0.0009130387,0.000001466265,0.001383069,0.002447546],"genre_scores_gemma":[0.9815277,0.0002217265,0.006579584,0.0001932772,0.0004618394,0.000007745874,0.0002177204,0.0001024867,0.01068789],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9844622,"threshold_uncertainty_score":0.9994234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05811504637595478,"score_gpt":0.2070428115423661,"score_spread":0.1489277651664113,"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."}}