{"id":"W7124178739","doi":"10.65109/muso7637","title":"Quasi deterministic POMDPs and DecPOMDPs","year":2010,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Observability; Observable; Extension (predicate logic); Class (philosophy); Markov decision process; Markov chain; Markov process","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006447912,0.0004294279,0.0003702588,0.0001875924,0.0004504679,0.001290801,0.001351299,0.0002983376,0.0005197821],"category_scores_gemma":[0.0004149383,0.0004142222,0.00009690086,0.0003731679,0.000330649,0.0006944973,0.001091036,0.0009661977,0.0007238974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002647044,"about_ca_system_score_gemma":0.0002592227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003313531,"about_ca_topic_score_gemma":0.00002958902,"domain_scores_codex":[0.9969857,0.00008983154,0.0006566935,0.0008640041,0.0005876025,0.0008161513],"domain_scores_gemma":[0.9972332,0.0004360627,0.0002527947,0.001402308,0.0001638929,0.0005118194],"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":[0.00003273788,0.0008266102,0.01923723,0.000401352,0.000234074,0.0003463502,0.007077913,0.009438531,0.004929475,0.6750807,0.002215619,0.2801794],"study_design_scores_gemma":[0.0005129144,0.0007746372,0.004249425,0.00003004143,0.00004534148,0.0002152137,0.00003647745,0.9714074,0.0004020917,0.000624135,0.02112656,0.0005757668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03140792,0.00007253057,0.9293935,0.0008704349,0.003693939,0.0003361209,7.499483e-7,0.0003227007,0.03390216],"genre_scores_gemma":[0.8748215,0.00008198733,0.1168172,0.0006497087,0.0002435252,0.000006383917,9.336104e-7,0.0000289072,0.007349806],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9619688,"threshold_uncertainty_score":0.999831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01220520026192275,"score_gpt":0.2520283231446702,"score_spread":0.2398231228827474,"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."}}