{"id":"W3037098147","doi":"","title":"Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning","year":2019,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; McGill University","funders":"","keywords":"Observability; Sample complexity; Reinforcement learning; Computer science; Observable; Artificial intelligence; Sample (material); Plan (archaeology); Mathematical optimization; Algorithm; Machine learning; 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":[0.002510894,0.0008022028,0.0009370579,0.0006405871,0.0004650482,0.001035866,0.001326261,0.001151819,0.00190162],"category_scores_gemma":[0.009926554,0.0004935723,0.0005258848,0.0006821807,0.002418857,0.002920836,0.001893119,0.001355144,0.0002748579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00123737,"about_ca_system_score_gemma":0.002518277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003219389,"about_ca_topic_score_gemma":0.002472323,"domain_scores_codex":[0.9987765,0.0005656009,0.000058696,0.0002133738,0.0002730668,0.000112764],"domain_scores_gemma":[0.9950662,0.003540054,0.0004610542,0.0004521712,0.0003128304,0.0001677081],"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":[0.0000925702,0.00007247399,0.0003935886,0.00008474328,0.00002638102,0.00004467936,0.00009427893,0.8102442,0.001217176,0.1269394,0.0006857804,0.06010478],"study_design_scores_gemma":[0.000008626215,0.00001934479,0.00004241148,0.000005604985,0.000002109092,0.000008928393,0.000006548031,0.9540047,0.0003871549,0.04533071,0.0001799281,0.000003967153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00740631,0.00004949765,0.9914899,0.00009626046,0.00000829021,0.00001888149,0.00001150496,0.0001585534,0.0007608489],"genre_scores_gemma":[0.6436853,0.0001538993,0.3540305,0.0001179147,0.00004271395,0.0001882961,0.00009593479,0.0001152131,0.001570229],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003219389,"threshold_uncertainty_score":0.01327902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09226570585973484,"score_gpt":0.3228543093033689,"score_spread":0.230588603443634,"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."}}