{"id":"W7097981727","doi":"","title":"Author manuscript, published in "Advances in Neural Information Processing Systems, Canada (2008)" Particle Filter-based Policy Gradient in POMDPs","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Parameterized complexity; Resampling; Particle filter; Measure (data warehouse); Markov decision process; Variance (accounting); Process (computing); Markov process; Filter (signal processing)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001814342,0.0009865378,0.00176412,0.001536448,0.001216402,0.005730611,0.001725667,0.002049784,0.3161965],"category_scores_gemma":[0.008700668,0.0007275486,0.0006952229,0.00279719,0.001116289,0.002648662,0.001644354,0.001517485,0.08234867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002748997,"about_ca_system_score_gemma":0.003662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0159487,"about_ca_topic_score_gemma":0.03321528,"domain_scores_codex":[0.9991872,0.0001057661,0.00006467746,0.0002845396,0.0002701906,0.0000877399],"domain_scores_gemma":[0.9964862,0.0006885018,0.0001154036,0.0004233517,0.001921187,0.0003653824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003105616,0.00009073412,0.001133029,0.0006033781,0.0001460317,0.000288069,0.0001282611,0.006387056,0.001760651,0.0278157,0.7147443,0.2465923],"study_design_scores_gemma":[0.00007748625,0.00006775766,0.001265693,0.0003116727,0.00005573445,0.0002802225,0.0001220173,0.02226259,0.002853888,0.0179081,0.9547449,0.00004999984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.009946349,0.03557477,0.2358946,0.05326576,0.1937096,0.0007364536,0.01772306,0.007508059,0.4456414],"genre_scores_gemma":[0.03469351,0.01210161,0.0641729,0.002134044,0.005420004,0.0001691764,0.006546995,0.001852299,0.8729094],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3161965,"threshold_uncertainty_score":0.9753627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02387122745405698,"score_gpt":0.2540971173766306,"score_spread":0.2302258899225736,"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."}}