{"id":"W4414746796","doi":"10.3390/sym17101632","title":"A Survey of Maximum Entropy-Based Inverse Reinforcement Learning: Methods and Applications","year":2025,"lang":"en","type":"article","venue":"Symmetry","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Ambiguity; Reinforcement learning; Benchmark (surveying); Principle of maximum entropy; Matching (statistics); Inverse","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":[0.002382648,0.001687696,0.00227098,0.001486345,0.0003930139,0.001633193,0.001664524,0.001518719,0.00281453],"category_scores_gemma":[0.005883896,0.0008122942,0.001235115,0.001824536,0.001190532,0.001634937,0.001575093,0.002227164,0.000958637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001276365,"about_ca_system_score_gemma":0.001393265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00265868,"about_ca_topic_score_gemma":0.001785785,"domain_scores_codex":[0.9988427,0.0004188809,0.0001185555,0.0002060722,0.0003643402,0.00004938031],"domain_scores_gemma":[0.9975305,0.001800459,0.000157397,0.0001214499,0.0003208646,0.00006933718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009449231,0.0001517944,0.001210584,0.002110874,0.0001860053,0.0001005307,0.0001762481,0.3880529,0.002289499,0.08531741,0.005548563,0.5147611],"study_design_scores_gemma":[0.00002393916,0.000140484,0.0004236824,0.0003470949,0.00004937476,0.0001375392,0.00003147697,0.9148386,0.001489695,0.06123801,0.02121709,0.00006298894],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.001811904,0.06006658,0.9307208,0.0006842148,0.0001649483,0.00005365117,0.00005749773,0.0002688113,0.006171559],"genre_scores_gemma":[0.3008227,0.151249,0.5334632,0.00101196,0.001670845,0.0007031122,0.0005011642,0.0004908612,0.01008709],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.00281453,"threshold_uncertainty_score":0.01260084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02304166197990325,"score_gpt":0.322562583324321,"score_spread":0.2995209213444178,"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."}}