{"id":"W137325057","doi":"10.1609/aaai.v26i1.8319","title":"Approximate Policy Iteration with Linear Action Models","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates - Technology Futures","keywords":"Benchmark (surveying); Computer science; Action (physics); Mathematical optimization; Linear model; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002499496,0.0001831637,0.0001839335,0.0001234383,0.0001988437,0.0003713414,0.0009817776,0.00007344024,0.0000207106],"category_scores_gemma":[0.0002270853,0.0001339777,0.00006717301,0.0009342728,0.0001258041,0.0009009074,0.000278634,0.0002758847,0.00003515125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006645644,"about_ca_system_score_gemma":0.0002541709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002219716,"about_ca_topic_score_gemma":0.00000476859,"domain_scores_codex":[0.9983486,0.00001836633,0.0003881627,0.0004103982,0.0005519257,0.000282542],"domain_scores_gemma":[0.9982091,0.00004278062,0.0003384989,0.0003336522,0.00101005,0.00006590266],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002699538,0.00004880081,0.00003394106,0.00003568961,0.00001214042,6.057008e-7,0.000924018,0.117277,0.01981679,0.8484454,0.00001941844,0.01335919],"study_design_scores_gemma":[0.0000173351,0.00009364675,0.00001503517,0.0001023471,0.000005231878,0.000007533041,0.0001769596,0.6102195,0.3456791,0.04354263,0.00003424531,0.0001064382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01742658,0.000006014081,0.9644967,0.003932693,0.0001869945,0.000232238,9.991127e-7,0.0001070177,0.01361073],"genre_scores_gemma":[0.9766212,0.00003578874,0.0221551,0.0002542939,0.00009155914,0.00001557141,0.000001165535,0.00001221366,0.0008131003],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9591946,"threshold_uncertainty_score":0.5463453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.12002286483175,"score_gpt":0.3180867896487678,"score_spread":0.1980639248170178,"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."}}