{"id":"W2519270595","doi":"","title":"Multi-step linear Dyna-style planning","year":2009,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Iterated function; Projection (relational algebra); Linear model; Feature (linguistics); Algorithm; Mathematics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001605432,0.0001133042,0.0001082479,0.00007622178,0.0001034764,0.0001252934,0.00071695,0.00005265566,0.00003903994],"category_scores_gemma":[0.00005462879,0.000099642,0.00004417645,0.0002205687,0.00001443315,0.0003529494,0.0001204725,0.0001557779,0.000348473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002678861,"about_ca_system_score_gemma":0.00002376113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008529351,"about_ca_topic_score_gemma":5.007544e-7,"domain_scores_codex":[0.9990165,0.00002277189,0.0001885188,0.0002474423,0.0002383355,0.0002864641],"domain_scores_gemma":[0.9992909,0.00004370545,0.00006131876,0.0004757199,0.0000425862,0.00008580903],"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":[0.000002098999,0.00003259748,0.0007855841,0.000003711163,0.000008183252,0.00002808617,0.0005818968,0.9733388,0.0006275178,0.008930794,0.00172711,0.01393362],"study_design_scores_gemma":[0.0002599121,0.0001074398,0.002827442,0.00001202,0.000001642331,0.000006706985,0.00002088052,0.9872354,0.0003964122,0.0000179263,0.008973896,0.0001403005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005421899,0.0000227357,0.9753914,0.000561257,0.0001845298,0.00007870451,8.004178e-8,0.0004334099,0.02278569],"genre_scores_gemma":[0.2711844,0.000002094629,0.7177078,0.001365624,0.000067115,0.000001197439,0.000001795893,0.000005458837,0.00966452],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2706422,"threshold_uncertainty_score":0.4479032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03563773707662921,"score_gpt":0.3005928994693765,"score_spread":0.2649551623927473,"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."}}