{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009650646,0.0008828427,0.001102281,0.0003745417,0.0003907992,0.001035346,0.001001786,0.001189973,0.006524146],"category_scores_gemma":[0.005832674,0.0004059833,0.0003059603,0.0004668394,0.00133043,0.001436411,0.001890366,0.001266539,0.0006180778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009976408,"about_ca_system_score_gemma":0.0009828283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003183447,"about_ca_topic_score_gemma":0.002285379,"domain_scores_codex":[0.9993551,0.0002225873,0.00002989525,0.0001727037,0.0001354016,0.00008418824],"domain_scores_gemma":[0.9980286,0.001238515,0.000148171,0.0001806703,0.0002584429,0.0001457306],"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":[0.0002368683,0.00008823974,0.0004320483,0.0001329173,0.0000445337,0.00008545804,0.00004251,0.8427047,0.001519534,0.09946688,0.00337268,0.05187372],"study_design_scores_gemma":[0.0000202717,0.00003177453,0.00007608325,0.00000794145,0.000004967699,0.00001311118,0.000004286654,0.978216,0.000332195,0.02069912,0.0005896626,0.000004662162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02762546,0.0006804053,0.9554843,0.0005096963,0.0001221433,0.00006332522,0.0001139037,0.0004121931,0.01498857],"genre_scores_gemma":[0.9422298,0.0003126701,0.0463503,0.0002116998,0.00006872074,0.0001516926,0.0001792892,0.00009292757,0.01040289],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006524146,"threshold_uncertainty_score":0.02182543,"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."}}