{"id":"W2966675798","doi":"10.24963/ijcai.2019/506","title":"Planning with Expectation Models","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Convergence (economics); Parametrization (atmospheric modeling); Mathematical optimization; Bellman equation; Function (biology); State (computer science); Artificial intelligence; Mathematics; Algorithm","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":[0.00004659899,0.00004819756,0.00004697615,0.00003970838,0.00002487111,0.00007771475,0.0002487342,0.00001495507,0.00002708279],"category_scores_gemma":[0.000002090678,0.00003570171,0.000009112304,0.0001118621,0.000004891805,0.000613972,0.00005049217,0.00004688035,0.0001654676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001272794,"about_ca_system_score_gemma":0.00001728143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003821785,"about_ca_topic_score_gemma":1.210356e-7,"domain_scores_codex":[0.9995086,0.00000819735,0.00006422522,0.0001329708,0.000176601,0.0001093853],"domain_scores_gemma":[0.9996504,0.00002600741,0.00003256097,0.000241816,0.00002667151,0.00002259916],"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":[0.000001273852,0.000001464737,0.001918204,0.000001993276,0.000002874574,0.000001120968,0.0006787791,0.9392399,0.00005581736,0.05785143,0.00006809401,0.000179086],"study_design_scores_gemma":[0.0001381847,0.00007710301,0.0005978539,0.00001015477,6.103295e-7,0.000002917369,0.00008339698,0.9983399,0.0002803694,0.000271993,0.0001305133,0.00006698293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01784531,0.00000385082,0.8836523,0.00006845799,0.00006285409,0.00006644913,8.560996e-9,0.0001435236,0.09815723],"genre_scores_gemma":[0.8643167,2.566924e-7,0.131153,0.0001254366,0.000007047723,0.000001987924,6.120027e-7,0.000003436282,0.004391518],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8464714,"threshold_uncertainty_score":0.2126807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01667274162100398,"score_gpt":0.2247960668066918,"score_spread":0.2081233251856878,"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."}}