{"id":"W2970673985","doi":"","title":"Learning Reward Machines for Partially Observable Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Observable; Computer science; Set (abstract data type); Artificial intelligence; Task (project management); Function (biology); Optimization problem; Learning automata; Representation (politics); Decomposition; Automaton; Mathematical optimization; Mathematics; Algorithm","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008830244,0.0002789035,0.0003320725,0.0002138819,0.000553664,0.001821588,0.0007516076,0.0001257219,0.00001136617],"category_scores_gemma":[0.0002567891,0.0002555068,0.0001022013,0.0004376958,0.0000226888,0.006584779,0.0001951567,0.0004129688,0.0002929382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001217907,"about_ca_system_score_gemma":0.0001364991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003499133,"about_ca_topic_score_gemma":4.51405e-7,"domain_scores_codex":[0.9973937,0.0000944909,0.0009842963,0.0002811645,0.0006781304,0.0005682698],"domain_scores_gemma":[0.9979908,0.0001288381,0.0009218098,0.0003636054,0.0004833209,0.0001115762],"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":[0.00001514339,0.00000347514,0.002632578,0.0006796154,0.00001226162,3.498836e-7,0.001706493,0.9819648,0.0001934208,0.002982631,0.0002998197,0.009509437],"study_design_scores_gemma":[0.0006109511,0.0003706492,0.0001367024,0.0001764991,0.000008109301,0.00001517818,0.0003079328,0.9319536,0.0001907849,0.00001785652,0.0659144,0.0002973376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009366598,0.00008347839,0.9795047,0.0002750418,0.001395325,0.001058049,4.179181e-7,0.0008256857,0.0074907],"genre_scores_gemma":[0.9865053,0.000006601485,0.004238817,0.0003093034,0.0001232695,0.0001267489,0.00007649868,0.00002221604,0.008591196],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9771388,"threshold_uncertainty_score":0.9999897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02100086568913788,"score_gpt":0.2534669585508525,"score_spread":0.2324660928617146,"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."}}