{"id":"W3169135197","doi":"10.1109/iccma53594.2021.00018","title":"Hyperspace Neighbor Penetration Approach to Dynamic Programming for Model-Based Reinforcement Learning Problems with Slowly Changing Variables in a Continuous State Space","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Telus (Canada)","funders":"","keywords":"Reinforcement learning; Hyperspace; Computer science; Grid; Mathematical optimization; State variable; Computation; Tile; Theoretical computer science; Algorithm; Mathematics; Artificial intelligence; Geometry; Physics","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001417827,0.000694528,0.0007585516,0.000839469,0.0002613038,0.001675152,0.001131373,0.000264549,0.000002818472],"category_scores_gemma":[0.0001650441,0.0006654788,0.0001594304,0.001084234,0.00004086018,0.0004849456,0.001060026,0.0009458706,0.000002314336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006666534,"about_ca_system_score_gemma":0.0009893567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001826845,"about_ca_topic_score_gemma":0.00008977341,"domain_scores_codex":[0.9954761,0.0001432525,0.0007298538,0.001570689,0.0008385542,0.001241497],"domain_scores_gemma":[0.9974677,0.0001594964,0.0006060209,0.001043637,0.000510167,0.000213007],"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":[0.00004502416,0.00008079837,0.00022268,0.0008677294,0.0000711528,0.000005905544,0.006207671,0.9863061,0.0001918946,0.003929244,0.000007566981,0.002064284],"study_design_scores_gemma":[0.001110758,0.0004671804,0.00002244858,0.000906328,0.00003771372,0.000004383953,0.000811489,0.9953241,0.0002065888,0.00006092234,0.0001904556,0.0008576331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00262646,0.00005542452,0.9891129,0.0005050729,0.0001732399,0.005069082,0.000001175907,0.0004763478,0.001980334],"genre_scores_gemma":[0.4180527,0.000008102662,0.576707,0.0001146438,0.00001746074,0.001226155,0.0001560279,0.0000622307,0.003655658],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4154263,"threshold_uncertainty_score":0.9995797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01664104467525781,"score_gpt":0.2406334646722556,"score_spread":0.2239924199969978,"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."}}