{"id":"W4402596039","doi":"10.21203/rs.3.rs-4314484/v1","title":"On-policy Actor-Critic Reinforcement Learning for Multi-UAV Exploration","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"","keywords":"Reinforcement learning; Policy learning; Computer science; Reinforcement; Artificial intelligence; Psychology; Social psychology; Machine learning","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":[0.001539367,0.001030492,0.00150609,0.0004077062,0.0004727864,0.00079627,0.001113562,0.001589363,0.003343712],"category_scores_gemma":[0.00508705,0.0006243421,0.0004420491,0.0003959721,0.001242817,0.0009597995,0.001660152,0.001883751,0.0004349034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001188457,"about_ca_system_score_gemma":0.001353676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007175099,"about_ca_topic_score_gemma":0.004980762,"domain_scores_codex":[0.9994997,0.0002041193,0.00002186703,0.00009064392,0.00009054189,0.00009304683],"domain_scores_gemma":[0.9980159,0.001397356,0.0001394547,0.0001071048,0.0002126722,0.0001274922],"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":[0.00008682521,0.00002595495,0.0001952092,0.00003109845,0.00001709931,0.00003083364,0.00002059247,0.9853705,0.0004018277,0.003684602,0.0005398277,0.009595697],"study_design_scores_gemma":[0.000008033463,0.00000966949,0.00002029562,0.000002290487,0.000001598767,0.000002264341,0.000001651356,0.998355,0.00007674328,0.001444108,0.00007710304,0.000001246193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02785453,0.0004148625,0.9664779,0.0004264585,0.000112267,0.00005172502,0.00004550261,0.0004014842,0.004215262],"genre_scores_gemma":[0.9417367,0.0001632173,0.05298434,0.0001370367,0.00005209023,0.0001150846,0.00007265837,0.00009026516,0.004648584],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007175099,"threshold_uncertainty_score":0.01426667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1819195764200979,"score_gpt":0.4539249079263171,"score_spread":0.2720053315062193,"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."}}