{"id":"W2808117931","doi":"10.65109/ohiq4340","title":"Faster Policy Adaptation in Environments with Exogeneity: A State Augmentation Approach","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Kernel (algebra); State (computer science); Embedding; Subspace topology; Variable (mathematics); State space; Function (biology); Q-learning; Variance (accounting); Artificial intelligence; Algorithm; Mathematics","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":[0.002301552,0.0009144843,0.001533949,0.0005023944,0.0004073989,0.0009380325,0.001449369,0.001258221,0.002306861],"category_scores_gemma":[0.007022907,0.0006756441,0.0006230877,0.0004394496,0.001314606,0.002500141,0.002195983,0.002265492,0.0004025856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005804811,"about_ca_system_score_gemma":0.001344307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002672307,"about_ca_topic_score_gemma":0.002032267,"domain_scores_codex":[0.9993542,0.0002544819,0.00004903421,0.0001686726,0.00009852614,0.00007502903],"domain_scores_gemma":[0.9961936,0.002538183,0.0003549171,0.0005063707,0.0002846988,0.0001221549],"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":[0.0002151215,0.0001490485,0.001104066,0.00007779625,0.00005981816,0.0001157888,0.000168029,0.8792643,0.003721708,0.01646229,0.0008913021,0.09777071],"study_design_scores_gemma":[0.000007268328,0.00001389184,0.00003298818,0.000002669603,0.000002504583,0.000007379438,0.00000261736,0.9968306,0.0002431706,0.002724492,0.0001300061,0.00000245896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01461257,0.0001683471,0.9835806,0.0002173352,0.00003736997,0.0000370868,0.00001971059,0.0005723523,0.0007546549],"genre_scores_gemma":[0.8257242,0.0001552059,0.1720104,0.0002731374,0.00007745162,0.0001657606,0.0000887569,0.0001045353,0.001400432],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002672307,"threshold_uncertainty_score":0.01217192,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02230516015929545,"score_gpt":0.2434765207205141,"score_spread":0.2211713605612186,"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."}}