{"id":"W2930281309","doi":"10.48550/arxiv.1904.01191","title":"Planning with Expectation Models","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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; Parametrization (atmospheric modeling); Convergence (economics); 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001129336,0.0002547748,0.0002360282,0.0002329905,0.000100047,0.0001634906,0.001429637,0.0001853446,0.000008843119],"category_scores_gemma":[0.000008945869,0.0002708866,0.00008257115,0.0003383713,0.00004549578,0.0006905291,0.001119936,0.0005201618,0.00009231018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001740947,"about_ca_system_score_gemma":0.0001870688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003142,"about_ca_topic_score_gemma":0.000001364732,"domain_scores_codex":[0.9985452,0.00006781927,0.000140479,0.0008155348,0.0001396099,0.0002913355],"domain_scores_gemma":[0.9983025,0.00007625933,0.0002835607,0.001120216,0.0001306716,0.00008680413],"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":[0.0000145133,0.00000930208,0.002066958,0.00003799006,0.00004725657,0.00009825522,0.0006936194,0.9372456,0.000003035927,0.05967932,0.0000735802,0.00003059001],"study_design_scores_gemma":[0.0003235267,0.00007481882,0.0003930831,0.0001446457,0.00002781589,0.00000304645,0.000122521,0.9946331,0.0000262237,0.003846328,0.00006100817,0.0003438331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04830114,0.00001841563,0.9385781,0.00002608111,0.0003299234,0.0002484556,9.227472e-7,0.0002848172,0.0122121],"genre_scores_gemma":[0.9871695,0.00001706975,0.009301573,0.00005121808,0.00003269067,6.294429e-7,0.00001512794,0.00001891358,0.003393279],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9388683,"threshold_uncertainty_score":0.9999743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1031923110966533,"score_gpt":0.1905398815660638,"score_spread":0.08734757046941054,"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."}}