{"id":"W2952735266","doi":"10.48550/arxiv.1205.2606","title":"Exploring compact reinforcement-learning representations with linear regression","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Reinforcement; Regression; Linear regression; Artificial intelligence; Computer science; Machine learning; Mathematics; Statistics; Psychology; Social psychology","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"],"consensus_categories":[],"category_scores_codex":[0.0003514068,0.0004621959,0.0004077534,0.0004010441,0.0004660098,0.0002053973,0.001694669,0.0001875474,0.00006056856],"category_scores_gemma":[0.00008853874,0.0004485306,0.0001806985,0.0007525017,0.0001184226,0.001759476,0.001844292,0.001389616,0.0001858335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003360377,"about_ca_system_score_gemma":0.0001883703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001668132,"about_ca_topic_score_gemma":0.000004150615,"domain_scores_codex":[0.9975128,0.0002247327,0.0003317486,0.0009895231,0.0002923525,0.0006488647],"domain_scores_gemma":[0.9969368,0.0002079181,0.0006392862,0.001672436,0.0002317104,0.0003118567],"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":[0.00003190025,0.00002508787,0.01055429,0.00006549698,0.0001076706,0.00009724756,0.0008365398,0.9691879,0.00002074569,0.01885003,0.00009231612,0.0001307449],"study_design_scores_gemma":[0.0005410785,0.0001066616,0.002121001,0.0003852923,0.0000923328,0.000008315945,0.0002688492,0.994195,0.0002458777,0.0001540493,0.001297593,0.0005838998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04640301,0.00002501034,0.9414567,0.00008490869,0.0005862578,0.0003611496,8.089398e-7,0.0005780737,0.01050413],"genre_scores_gemma":[0.9881687,0.0002561381,0.00492278,0.00003495881,0.0001556179,0.000002477596,0.00005388043,0.00004046819,0.006364934],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9417657,"threshold_uncertainty_score":0.9997966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2191019035449421,"score_gpt":0.2371817989078626,"score_spread":0.01807989536292046,"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."}}