{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001556669,0.0005096855,0.001046569,0.0004391827,0.0003917183,0.0006637559,0.00155298,0.0009607542,0.002576322],"category_scores_gemma":[0.008541621,0.0003490151,0.0005966327,0.0003467103,0.001721592,0.002103584,0.002280256,0.001560348,0.0004064694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006624341,"about_ca_system_score_gemma":0.0006647799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001430254,"about_ca_topic_score_gemma":0.0009181009,"domain_scores_codex":[0.9990839,0.0004295068,0.00004077801,0.0002188416,0.0001303543,0.00009679075],"domain_scores_gemma":[0.9957885,0.00268358,0.0002999591,0.0006077836,0.000328652,0.0002914449],"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":[0.000302149,0.0005446013,0.003412288,0.0001315904,0.00007430567,0.0002098747,0.0003807173,0.7590613,0.004213738,0.02723184,0.001039669,0.2033979],"study_design_scores_gemma":[0.00001489191,0.00007958723,0.0001553796,0.000005950008,0.000003993024,0.00002236209,0.00002221157,0.9871495,0.0009168794,0.01147335,0.0001508219,0.000004992009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1728909,0.0001525259,0.8226511,0.0003472542,0.00002930993,0.0001117729,0.0000310328,0.0007595652,0.00302658],"genre_scores_gemma":[0.9687642,0.00004011203,0.02979789,0.00007245432,0.00001233394,0.000101272,0.00003359255,0.00002324586,0.001154815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002576322,"threshold_uncertainty_score":0.008618653,"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."}}