{"id":"W4406267575","doi":"10.1177/02783649241312699","title":"Shared autonomy policy fine-tuning and alignment for robotic tasks","year":2025,"lang":"en","type":"article","venue":"The International Journal of Robotics Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; McGill University","funders":"","keywords":"Reinforcement learning; Arbitration; Autonomy; Computer science; Human–computer interaction; Task (project management); Robot; Artificial intelligence; Controller (irrigation); Human–robot interaction; Distributed computing; Engineering; Systems engineering","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":[0.002682799,0.0001111137,0.0001803349,0.0007490598,0.0002463507,0.0007258453,0.002814197,0.00005054259,0.000006692352],"category_scores_gemma":[0.001288748,0.00008164854,0.00009361804,0.0004194948,0.00013906,0.0003426983,0.0009954352,0.000491727,0.000005930978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005001845,"about_ca_system_score_gemma":0.00109878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002565581,"about_ca_topic_score_gemma":0.000002995794,"domain_scores_codex":[0.9976901,0.0001476096,0.0005007579,0.0001738453,0.001159038,0.0003286692],"domain_scores_gemma":[0.996558,0.0013438,0.0002289006,0.0003252991,0.001452829,0.00009119244],"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":[0.00002866294,0.00002300621,0.0002326826,0.00001316637,0.0001656705,0.00001083615,0.0003459784,0.7455321,0.0004345142,0.2457277,0.003109674,0.00437607],"study_design_scores_gemma":[0.0008734284,0.0002107708,0.0007824517,0.000219077,0.00001503427,0.00006757109,0.0001128161,0.9665784,0.0006234076,0.02227117,0.008144974,0.0001009419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002984535,0.0001878462,0.9375236,0.05949237,0.0007275732,0.0002136329,8.512745e-7,0.00001278514,0.001542903],"genre_scores_gemma":[0.8616046,0.0001389652,0.1290048,0.0008479972,0.0006345169,0.00001582519,0.000003659244,0.00001784591,0.007731771],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8613062,"threshold_uncertainty_score":0.6999344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07345984979332178,"score_gpt":0.4058068460678118,"score_spread":0.33234699627449,"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."}}