{"id":"W4410537008","doi":"10.1007/s00521-025-11288-1","title":"Human-AI collaboration in real-world complex environment with reinforcement learning","year":2025,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Thales (Canada); Espace pour la vie; Network for Business Sustainability; University of Alberta","funders":"","keywords":"Computational Science and Engineering; Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Machine learning; Psychology; Social psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.0001640719,0.0001293665,0.0001399081,0.0001867705,0.0004624769,0.0002057124,0.0002805118,0.00002839878,0.000004417128],"category_scores_gemma":[0.000004926492,0.0001250378,0.0000152212,0.0006932114,0.00005781326,0.0001391628,0.0002213117,0.0002450328,0.000006533277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009029556,"about_ca_system_score_gemma":0.00003051334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006695365,"about_ca_topic_score_gemma":0.00003070646,"domain_scores_codex":[0.9989268,0.00005522682,0.0002935868,0.0003418924,0.0001716916,0.000210799],"domain_scores_gemma":[0.999411,0.00007343954,0.000123409,0.0003105763,0.00003844506,0.00004309983],"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":[0.000001572134,0.00001299095,0.009053546,0.00001489271,0.000005452252,6.585415e-7,0.0001344367,0.9030604,0.0003156298,0.08340684,0.0001009234,0.003892601],"study_design_scores_gemma":[0.0003723932,0.00007267662,0.02545156,0.00003458571,0.000006253757,0.00000113682,0.00006122151,0.9606989,0.0000852017,0.0002265964,0.01285346,0.000135997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01260669,0.00001523001,0.9764754,0.001507356,0.00002122183,0.000478129,1.582164e-7,0.0001635878,0.008732276],"genre_scores_gemma":[0.9900035,0.0000108487,0.007903192,0.0003998508,0.00002586398,0.00005004011,0.00001672166,0.000006181311,0.001583823],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9773968,"threshold_uncertainty_score":0.5098895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01931864816271456,"score_gpt":0.3100600253669215,"score_spread":0.290741377204207,"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."}}