{"id":"W2101911972","doi":"10.1109/robot.2010.5509717","title":"Apprenticeship learning via soft local homomorphisms","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Markov decision process; Computer science; Reinforcement learning; State space; Artificial intelligence; Robot; Process (computing); Markov process; Space (punctuation); Homomorphism; Apprenticeship; Machine learning; Mathematics; Discrete mathematics; Statistics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003675175,0.0001471279,0.0001300963,0.00008969117,0.0001937232,0.0002795372,0.00112317,0.0001013475,0.0003707934],"category_scores_gemma":[0.00009686065,0.0001329352,0.00006355924,0.0002741345,0.0001127865,0.0005038374,0.0003941282,0.0007343192,0.001110706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001472619,"about_ca_system_score_gemma":0.00003889029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001986021,"about_ca_topic_score_gemma":0.000006761793,"domain_scores_codex":[0.9986342,0.00004422705,0.0002209681,0.000335023,0.0003866034,0.0003789377],"domain_scores_gemma":[0.9989648,0.0001348341,0.0001011864,0.000583214,0.00007458306,0.0001414055],"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":[0.000003736599,0.00004588308,0.00419049,0.00002082977,0.00002657576,0.00002529642,0.0004516046,0.6966739,0.005280865,0.1827402,0.0007310185,0.1098097],"study_design_scores_gemma":[0.0001820835,0.0000696096,0.0007618583,0.000004205102,0.000004493694,0.00002768495,0.00002100827,0.981537,0.001778546,0.0007851907,0.01462793,0.0002003327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002747971,0.000005691496,0.9695766,0.0002751251,0.0008937541,0.00008530913,3.397423e-8,0.0005606486,0.02585485],"genre_scores_gemma":[0.9160135,0.000001056902,0.07709538,0.000225444,0.00008426502,0.000005159722,0.000002370763,0.00001260984,0.006560215],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9132655,"threshold_uncertainty_score":0.999667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008005428190261192,"score_gpt":0.2186784038764432,"score_spread":0.210672975686182,"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."}}