{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009484003,0.0007530184,0.001075201,0.0003580337,0.0003379878,0.0007963861,0.001112043,0.001046765,0.003205764],"category_scores_gemma":[0.002225538,0.0005117633,0.0009110595,0.0004335941,0.001111699,0.001331466,0.001629737,0.002318425,0.000339345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008079084,"about_ca_system_score_gemma":0.000851102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003925888,"about_ca_topic_score_gemma":0.002775484,"domain_scores_codex":[0.9994376,0.0002440196,0.00002150712,0.0001038723,0.0001338278,0.00005914123],"domain_scores_gemma":[0.9989998,0.000672028,0.00007882955,0.00006709473,0.0001187496,0.00006359348],"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":[0.00004826791,0.00002544346,0.0003556455,0.00006222542,0.00003133233,0.000066072,0.00006316322,0.9352021,0.001156183,0.043351,0.0005259546,0.01911268],"study_design_scores_gemma":[0.000002641363,0.00001004077,0.00001692381,0.00000221624,0.000001325415,0.000005276746,0.000002524953,0.994517,0.0001234071,0.005076912,0.0002396677,0.000002016009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004304818,0.0001023969,0.9943643,0.00008058836,0.00001919109,0.00001744305,0.00001557114,0.00008161004,0.001014265],"genre_scores_gemma":[0.6616724,0.0004287156,0.3320021,0.0003005038,0.00006447262,0.000409329,0.0001534071,0.0001880598,0.004780983],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003925888,"threshold_uncertainty_score":0.01072437,"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."}}