{"id":"W4413211058","doi":"10.2139/ssrn.5387658","title":"Experimental Study on the Effect of Multi-Step Deep Reinforcement Learning in Pomdps","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Space Satellite Systems and Control","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Mathematical optimization; Psychology; Mathematics; Social psychology","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002340025,0.0003716941,0.0005528735,0.0002520967,0.00008514455,0.00005196259,0.0004284491,0.0001603457,0.0000149323],"category_scores_gemma":[0.00003980709,0.0002594788,0.0002333191,0.0001295607,0.00001286702,0.00003360136,0.0001290293,0.004716473,0.000008114297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00168244,"about_ca_system_score_gemma":0.0003068565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001899247,"about_ca_topic_score_gemma":0.0003791814,"domain_scores_codex":[0.9972348,0.0003961569,0.000564873,0.0002270062,0.0003448416,0.001232348],"domain_scores_gemma":[0.9992694,0.0001560776,0.0001835184,0.0003243284,0.00002727922,0.00003935564],"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":[0.0002311349,0.0002457066,0.007896422,0.0001670203,0.001876326,0.00001450618,0.003929029,0.9719462,0.001323406,0.001732978,0.00001421779,0.01062302],"study_design_scores_gemma":[0.0210472,0.01774892,0.00352377,0.002608472,0.0006500014,0.0001139853,0.08085968,0.8494304,0.02004799,0.0005259628,0.001269133,0.002174526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9685018,0.01673661,0.009538066,0.00005748835,0.0009346183,0.00206981,8.07463e-7,0.000128045,0.002032764],"genre_scores_gemma":[0.9985682,0.0005409126,0.000007493062,0.00000696396,0.000121433,0.0001421759,0.000001947039,0.00003496374,0.0005759579],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1225159,"threshold_uncertainty_score":0.9999858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007431018518091173,"score_gpt":0.2500148783517177,"score_spread":0.2425838598336265,"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."}}