{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005758259,0.001386222,0.002589431,0.001843953,0.0003179344,0.002670021,0.002407305,0.001773327,0.002333201],"category_scores_gemma":[0.0249002,0.0007147221,0.001121142,0.002846934,0.001652604,0.00540449,0.001853953,0.002269119,0.000758059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001364905,"about_ca_system_score_gemma":0.002119983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002753429,"about_ca_topic_score_gemma":0.001741377,"domain_scores_codex":[0.9977716,0.0005878528,0.0002589066,0.0006436041,0.0006454478,0.00009248024],"domain_scores_gemma":[0.9824842,0.01450906,0.0004869011,0.000805641,0.00159855,0.000115633],"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":[0.0001264283,0.0001501144,0.001618788,0.005001589,0.0002617203,0.00006209358,0.0001360879,0.04911924,0.0006780318,0.06517655,0.004087844,0.8735815],"study_design_scores_gemma":[0.00009003968,0.0006874406,0.006533806,0.004544764,0.0007240117,0.0009246219,0.0004056522,0.4771586,0.003870997,0.4241764,0.08071999,0.0001636404],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.008214992,0.6322766,0.3478768,0.002570798,0.0002919273,0.00007881808,0.0001301218,0.0002417841,0.008318222],"genre_scores_gemma":[0.2654299,0.5730593,0.1528496,0.001168356,0.002812733,0.0002785139,0.0005344722,0.0002302891,0.003636796],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.005758259,"threshold_uncertainty_score":0.03045291,"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."}}