{"id":"W7124138561","doi":"10.65109/kjtg4247","title":"Efficient planning in R-max","year":2011,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Value (mathematics); Automated planning and scheduling; Markov decision process; Order (exchange); Active learning (machine learning)","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007232443,0.0002755773,0.0002703473,0.0003476467,0.0001199712,0.0001695399,0.001339171,0.0001394618,0.0009963934],"category_scores_gemma":[0.00009327609,0.0002718563,0.00008177425,0.0008550246,0.0001041256,0.0001702053,0.0007671166,0.0004562874,0.001051674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001181413,"about_ca_system_score_gemma":0.0001334375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001325437,"about_ca_topic_score_gemma":0.000002667679,"domain_scores_codex":[0.9973018,0.0001117511,0.0006648253,0.0006063232,0.0005075312,0.0008077828],"domain_scores_gemma":[0.9986537,0.00008774734,0.0001854326,0.0008344342,0.00006639146,0.0001723683],"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":[0.00001030538,0.00008651018,0.01307969,0.00001870493,0.00001057859,0.0001110491,0.01451015,0.9448639,0.00001670757,0.02415207,0.0001160221,0.003024326],"study_design_scores_gemma":[0.0004253316,0.0002108492,0.02226367,0.0001515134,0.000005395128,0.000009672669,0.0002474532,0.9755291,0.0003305519,0.00008222301,0.0004098567,0.000334422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01782086,0.0001198741,0.7641966,0.00005919601,0.001068621,0.0002030208,1.019912e-7,0.00009533282,0.2164363],"genre_scores_gemma":[0.9461052,0.000005904548,0.04922187,0.0002788236,0.00004125298,0.00000503351,3.643036e-7,0.00001571256,0.004325847],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9282843,"threshold_uncertainty_score":0.9999734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06178843939825616,"score_gpt":0.2670726314811488,"score_spread":0.2052841920828927,"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."}}