{"id":"W2947766523","doi":"10.24963/ijcai.2019/439","title":"Advantage Amplification in Slowly Evolving Latent-State Environments","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Stylized fact; Abstraction; Computer science; Reinforcement learning; Key (lock); Artificial intelligence; Action (physics); Machine learning; State (computer science); Task (project management); Algorithm; Computer security; Engineering","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":[0.004996234,0.0009902196,0.001432805,0.0007209885,0.0007465716,0.001758332,0.001766871,0.001448417,0.003167644],"category_scores_gemma":[0.02594482,0.0008164063,0.001072566,0.0005260933,0.002220139,0.004273853,0.005784857,0.003500861,0.0003540753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001371784,"about_ca_system_score_gemma":0.001192514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001714674,"about_ca_topic_score_gemma":0.001815648,"domain_scores_codex":[0.9974159,0.001120882,0.0001317367,0.0005076459,0.000517062,0.0003067277],"domain_scores_gemma":[0.9687216,0.02646234,0.001684184,0.001723303,0.0007232263,0.0006853614],"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":[0.0003884253,0.0001488449,0.00326383,0.0002615791,0.0001587881,0.000480892,0.0005919006,0.6826917,0.007109021,0.2469219,0.001787521,0.05619567],"study_design_scores_gemma":[0.00001693115,0.00005964249,0.0003302775,0.00001284447,0.00001375945,0.00005815635,0.00002751632,0.9084038,0.0008974125,0.08967974,0.0004834856,0.00001639276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0556611,0.000283885,0.9401986,0.000596614,0.00003420418,0.00005212571,0.00007267501,0.0003433116,0.002757533],"genre_scores_gemma":[0.9116946,0.0002795663,0.08392356,0.0002660153,0.00006363572,0.0001612829,0.000110087,0.0001349144,0.00336637],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004996234,"threshold_uncertainty_score":0.02642298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01805212001434894,"score_gpt":0.2516236503439548,"score_spread":0.2335715303296058,"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."}}