{"id":"W2034960258","doi":"10.1109/devlrn.2012.6400860","title":"Scaling life-long off-policy learning","year":2012,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Estimator; Artificial intelligence; Scaling; Convergence (economics); Machine learning; Scale (ratio); Value (mathematics); Coding (social sciences); Mathematics; Economics; Economic growth","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":[],"category_scores_codex":[0.0008610713,0.0004349161,0.0004431008,0.0004011794,0.0002488881,0.0008200998,0.002460937,0.0004199558,0.0001358598],"category_scores_gemma":[0.0009652107,0.0004234183,0.0002242118,0.0003797885,0.00006009888,0.0004682075,0.006291157,0.001916858,0.000823352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000196818,"about_ca_system_score_gemma":0.0005695464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001653045,"about_ca_topic_score_gemma":0.00000156107,"domain_scores_codex":[0.9969461,0.0001971146,0.0005861064,0.0007108364,0.0007118736,0.0008479949],"domain_scores_gemma":[0.9973803,0.0002476733,0.0004507656,0.00138079,0.0001490597,0.0003914014],"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":[0.000001095564,0.00001293458,0.00297847,0.00008680908,0.00005369012,0.000004784163,0.0007368334,0.9479091,0.00001061807,0.02391201,0.0003520269,0.0239416],"study_design_scores_gemma":[0.0001640301,0.00002228659,0.002427865,0.00015396,0.00002200224,0.00000958799,0.00002961811,0.9801235,0.0001235663,0.0004022268,0.01586468,0.0006567069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001214944,0.0004786552,0.9425294,0.001107337,0.001481574,0.0002504562,2.522031e-7,0.001054437,0.05188296],"genre_scores_gemma":[0.8664178,0.0002826218,0.1126645,0.0009394864,0.001793756,0.00002995899,0.00002509689,0.00006851876,0.01777827],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8652028,"threshold_uncertainty_score":0.9999546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03094341280881763,"score_gpt":0.287813299354403,"score_spread":0.2568698865455853,"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."}}