{"id":"W4388761312","doi":"10.17760/d20486919","title":"Bayesian partially observable reinforcement learning","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Science North","funders":"","keywords":"Computer science; Reinforcement learning; Inference; State (computer science); Bayesian inference; Artificial intelligence; Bayesian probability","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004655158,0.0004190374,0.0003961033,0.0002820416,0.0003326373,0.0005910479,0.001591015,0.0003270063,0.0003303113],"category_scores_gemma":[0.0002146804,0.0004199275,0.0001868786,0.0006896991,0.00001410583,0.0004705326,0.0002487228,0.0007559665,0.002274244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001240236,"about_ca_system_score_gemma":0.0003114757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001417121,"about_ca_topic_score_gemma":0.0001269005,"domain_scores_codex":[0.9969113,0.00007718404,0.0006831023,0.0006839483,0.0009522812,0.0006921338],"domain_scores_gemma":[0.9981958,0.0001348252,0.0004296711,0.0008858491,0.0001883669,0.0001654965],"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":[0.000006656617,0.000005767454,0.0001190195,0.000113133,0.00006251719,0.00002400231,0.0009960781,0.978503,0.00006356441,0.01217325,0.004873233,0.003059753],"study_design_scores_gemma":[0.0002171467,0.0001821477,0.0005649876,0.0001703281,0.00002758013,0.000001493685,0.0003635337,0.9713274,0.0007449593,0.0002562709,0.02556098,0.0005832347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.0001466357,0.00002897001,0.8607444,0.0001264812,0.002398156,0.000336184,1.009627e-7,0.001579345,0.1346398],"genre_scores_gemma":[0.05841697,0.00014746,0.01322951,0.0002038996,0.0001856944,0.00008719543,0.0007176399,0.000104973,0.9269066],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8475149,"threshold_uncertainty_score":0.9998252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02529112251535362,"score_gpt":0.2726790296713985,"score_spread":0.2473879071560448,"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."}}