{"id":"W4414321910","doi":"10.1109/tai.2025.3610590","title":"Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick; University of Windsor; Toronto Metropolitan University","funders":"","keywords":"Generalization; Inverse; Transfer (computing); Stability (learning theory); Calculus (dental)","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":[0.0002093,0.0001956133,0.0002622498,0.0002720797,0.0002191546,0.0001116654,0.0002745845,0.00008592828,0.00002579277],"category_scores_gemma":[0.00004429177,0.0001880617,0.00007373361,0.0009797991,0.000159639,0.0002670666,0.000008680337,0.0003003074,0.000003982702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003547206,"about_ca_system_score_gemma":0.00007136519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003889856,"about_ca_topic_score_gemma":0.00001041618,"domain_scores_codex":[0.9985077,0.0001151058,0.0005333903,0.0003709261,0.0002691181,0.0002036922],"domain_scores_gemma":[0.9991231,0.0001729214,0.00007568784,0.0003091421,0.0002460098,0.000073127],"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":[0.00002081155,0.00003729216,0.000004743812,0.0005878291,0.00003007506,0.000002148694,0.001345142,0.8918725,0.001140969,0.03250888,0.00002153594,0.07242813],"study_design_scores_gemma":[0.00006744924,0.0003019464,0.00001269011,0.001697139,0.00005052298,0.000006451856,0.00009324472,0.9499424,0.04561146,0.0008558003,0.001152961,0.0002080096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008099105,0.001461649,0.9960649,0.0006163243,0.0003099856,0.0004171516,0.000003141278,0.00007511005,0.0002418295],"genre_scores_gemma":[0.9586648,0.02851508,0.01131067,0.001149393,0.00001322365,0.00003425372,0.000006746539,0.00001147139,0.0002943484],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9847542,"threshold_uncertainty_score":0.7668933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03715181315305159,"score_gpt":0.2995708591001717,"score_spread":0.2624190459471201,"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."}}