{"id":"W4283801867","doi":"10.1609/aaai.v36i7.20764","title":"Blockwise Sequential Model Learning for Partially Observable Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Observable; Reinforcement learning; Computer science; Latent variable; Block (permutation group theory); Artificial intelligence; Artificial neural network; Markov process; Variable (mathematics); Machine learning; Markov chain; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001002782,0.0007715719,0.00113126,0.0003088909,0.0003035418,0.0005543325,0.001339428,0.0008452164,0.002510194],"category_scores_gemma":[0.002425589,0.0004980113,0.000543679,0.0003238453,0.0007280681,0.001133527,0.001002642,0.00153919,0.0003617559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008541271,"about_ca_system_score_gemma":0.001403486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005719339,"about_ca_topic_score_gemma":0.006396289,"domain_scores_codex":[0.9995372,0.000153531,0.00002127224,0.0001097107,0.0001218658,0.00005627282],"domain_scores_gemma":[0.9992274,0.0004146658,0.00009442601,0.00007646989,0.0001334706,0.00005353509],"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":[0.00005393478,0.00004046893,0.0003827495,0.00005210552,0.00003377883,0.0000415238,0.00004131114,0.9466303,0.00163241,0.0184304,0.000714279,0.0319468],"study_design_scores_gemma":[0.000002682454,0.000009788532,0.00001575183,8.892857e-7,0.000001422869,0.00000251616,7.241877e-7,0.9976462,0.0001102666,0.002103916,0.0001045734,0.000001245707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007072716,0.00009552078,0.9918677,0.00008096027,0.00002696838,0.00001978562,0.00002469735,0.0002205067,0.0005910659],"genre_scores_gemma":[0.8208391,0.0002352076,0.17422,0.000165328,0.00006279052,0.0002531494,0.0002101355,0.0001006194,0.003913592],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005719339,"threshold_uncertainty_score":0.01137209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0468047699607824,"score_gpt":0.2675118803325101,"score_spread":0.2207071103717277,"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."}}