{"id":"W2152103449","doi":"10.1109/robot.2007.363632","title":"A formal framework for robot learning and control under model uncertainty","year":2007,"lang":"en","type":"article","venue":"Proceedings - IEEE International Conference on Robotics and Automation/Proceedings","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Partially observable Markov decision process; A priori and a posteriori; Computer science; Robot; Markov decision process; Observable; Domain (mathematical analysis); Markov process; Process (computing); Artificial intelligence; Control (management); Simple (philosophy); Machine learning; Markov chain; Markov model; Mathematics","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":[0.002991268,0.001541808,0.001224072,0.0009913198,0.001091179,0.002910723,0.003185447,0.00208585,0.004710471],"category_scores_gemma":[0.005841819,0.0007390614,0.002291437,0.00140885,0.004401325,0.003648791,0.002911567,0.004327301,0.0009091054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001718591,"about_ca_system_score_gemma":0.002576458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004134722,"about_ca_topic_score_gemma":0.003886952,"domain_scores_codex":[0.9978712,0.00080845,0.0001639818,0.0003575899,0.0006178848,0.0001808787],"domain_scores_gemma":[0.9974664,0.001688871,0.0002476145,0.0003015965,0.0001847255,0.0001107999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001705285,0.00002610369,0.0001133627,0.0001303117,0.00002661075,0.0001342073,0.0001051438,0.1226858,0.0005215702,0.8603928,0.001246647,0.01460037],"study_design_scores_gemma":[0.00004461161,0.00005713639,0.00006464135,0.00007531711,0.00002236721,0.0001094179,0.00004673732,0.3768619,0.0005534153,0.6052368,0.01690556,0.00002205945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004220909,0.0002583387,0.9968808,0.0003442342,0.00003665504,0.00002968107,0.00004468955,0.0001266049,0.001856978],"genre_scores_gemma":[0.1404098,0.001485413,0.8517993,0.0004602465,0.0003361197,0.0009025466,0.0002950946,0.0001308957,0.004180567],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004710471,"threshold_uncertainty_score":0.01581955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03111409225815821,"score_gpt":0.312915184565104,"score_spread":0.2818010923069458,"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."}}