{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001694769,0.0004604384,0.0006385627,0.000332409,0.0006807363,0.0009902376,0.001140018,0.0008641655,0.002050564],"category_scores_gemma":[0.004725123,0.0002592556,0.0003100708,0.0002585837,0.001116323,0.001582281,0.002434208,0.0009652086,0.0002534232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005543488,"about_ca_system_score_gemma":0.0009943254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002697486,"about_ca_topic_score_gemma":0.002364481,"domain_scores_codex":[0.9992064,0.0003877522,0.00002467639,0.0001643016,0.0001069172,0.0001099313],"domain_scores_gemma":[0.9976636,0.001206324,0.0002312864,0.0002559329,0.0002439819,0.000398892],"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":[0.0005987869,0.000511141,0.005272231,0.0001146643,0.0001529283,0.000512874,0.0008792265,0.8886016,0.008015586,0.01914635,0.001438425,0.07475617],"study_design_scores_gemma":[0.00001879928,0.00007268419,0.00034498,0.000003858265,0.000008849809,0.00002929454,0.00008601772,0.9901752,0.0006515388,0.008253828,0.0003477184,0.00000718425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2859248,0.0002847564,0.7037283,0.0006296011,0.00009791481,0.000112756,0.00003072579,0.0005752674,0.008615831],"genre_scores_gemma":[0.9785452,0.00003331212,0.02041517,0.00002922219,0.000008707123,0.00003151781,0.00001049108,0.00001391251,0.00091234],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002697486,"threshold_uncertainty_score":0.008962929,"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."}}