{"id":"W4389395619","doi":"10.1007/s10458-023-09607-8","title":"Uniformly constrained reinforcement learning","year":2023,"lang":"en","type":"article","venue":"Autonomous Agents and Multi-Agent Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Exploratory Research for Advanced Technology","keywords":"Reinforcement learning; Markov decision process; Mathematical optimization; Operator (biology); Counterexample; Probabilistic logic; Context (archaeology); Computer science; Heuristic; Constraint (computer-aided design); Monotonic function; Markov process; Mathematics; Artificial intelligence","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"],"consensus_categories":[],"category_scores_codex":[0.0007425547,0.0003024093,0.0003325786,0.0002737012,0.0004747839,0.0005043563,0.0006014588,0.0001131736,0.00002090005],"category_scores_gemma":[0.00006675496,0.0002772574,0.00008699841,0.0004512795,0.00007357893,0.0004049147,0.000494472,0.0002455379,0.0006371072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001233007,"about_ca_system_score_gemma":0.00009985054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000201536,"about_ca_topic_score_gemma":0.000002196738,"domain_scores_codex":[0.9975739,0.0001142136,0.0006312952,0.0005437264,0.0004529827,0.0006839052],"domain_scores_gemma":[0.998746,0.00008953743,0.0003010334,0.0005279179,0.0000851294,0.0002503404],"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":[0.000002131181,0.00001861299,0.002719218,0.00009860898,0.00009120273,0.00007282429,0.001942393,0.9805279,0.0002079779,0.009686578,0.00167692,0.002955642],"study_design_scores_gemma":[0.0008601074,0.0001270528,0.003126947,0.00006706882,0.00001300567,0.00002652875,0.0004760858,0.9354092,0.0000359511,0.000004595324,0.05953708,0.0003163065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01567437,0.0001092069,0.9742734,0.0002566894,0.001858122,0.0009206998,0.000002094269,0.001297945,0.005607435],"genre_scores_gemma":[0.9623129,0.0001513691,0.001991423,0.0001536921,0.00006928064,0.00006198142,0.00004116448,0.00002911661,0.03518905],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.972282,"threshold_uncertainty_score":0.9999679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04139100013431038,"score_gpt":0.2750660092176482,"score_spread":0.2336750090833378,"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."}}