{"id":"W178133203","doi":"10.1609/aaai.v25i1.7796","title":"Policy Gradient Planning for Environmental Decision Making with Existing Simulators","year":2011,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Forest Management and Policy","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Parameterized complexity; Computer science; Markov chain; Markov decision process; Domain (mathematical analysis); Operations research; Mathematical optimization; Markov process; Machine learning; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002687222,0.0002122384,0.0001691883,0.00009932391,0.0002716623,0.00005647706,0.0007035191,0.00005411418,0.0007167485],"category_scores_gemma":[0.0001572114,0.0001479287,0.00008313818,0.0003133489,0.0004060678,0.0002276378,0.000304553,0.0001321807,0.000158787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008575188,"about_ca_system_score_gemma":0.0000124372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007689415,"about_ca_topic_score_gemma":0.00001165078,"domain_scores_codex":[0.998524,0.000005912739,0.0003474319,0.0003730408,0.0003661939,0.0003834951],"domain_scores_gemma":[0.9993732,0.00007430558,0.0002953741,0.0001661493,0.00001952593,0.00007147152],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001673288,0.0005249541,0.08576612,0.00008013496,0.00005792182,0.000002342281,0.01411115,0.003870702,0.01022595,0.5575286,0.000799133,0.3253597],"study_design_scores_gemma":[0.0004120299,0.003059221,0.03521876,0.002001732,0.0001923306,0.00001971329,0.005675014,0.170864,0.2437088,0.5341272,0.002721784,0.001999317],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8882524,0.000003733084,0.001883006,0.0001349714,0.0001048948,0.0006083962,0.000006577381,0.00003938765,0.1089666],"genre_scores_gemma":[0.9948509,0.000003875506,0.004284942,0.0001469318,0.00006098565,0.00003128523,5.56878e-7,0.00002129199,0.0005992231],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3233604,"threshold_uncertainty_score":0.7847893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1054500535485158,"score_gpt":0.315841546250156,"score_spread":0.2103914927016401,"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."}}