{"id":"W3210129106","doi":"10.48550/arxiv.2111.00876","title":"On the Expressivity of Markov Reward","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Set (abstract data type); Markov chain; Computer science; Task (project management); Expressivity; Reinforcement learning; Function (biology); Frame (networking); Construct (python library); Markov decision process; Markov process; Artificial intelligence; Machine learning; Cognitive psychology; Psychology; Mathematics; Programming language; Statistics","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":[0.00517846,0.0009983638,0.0009211414,0.0006529067,0.000767999,0.002629353,0.001341792,0.001518586,0.00264991],"category_scores_gemma":[0.02685561,0.0005831264,0.0009340566,0.0007611347,0.005090751,0.007879413,0.002058968,0.004448504,0.000380933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003062204,"about_ca_system_score_gemma":0.001985344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002801865,"about_ca_topic_score_gemma":0.002508294,"domain_scores_codex":[0.9955142,0.00246526,0.0002536625,0.0006506038,0.0007431727,0.0003731656],"domain_scores_gemma":[0.9799084,0.0151862,0.001465915,0.001818751,0.0009813845,0.0006393401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001145799,0.00004874924,0.001159404,0.00008091912,0.00003192425,0.00006195581,0.000270916,0.162262,0.001229367,0.818228,0.001038251,0.01547379],"study_design_scores_gemma":[0.00001799342,0.00005197971,0.0002131656,0.00002746085,0.00001023936,0.00003454319,0.00003349642,0.4029739,0.0005857248,0.5948443,0.001191998,0.00001516168],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03335058,0.0003277373,0.9563185,0.00204997,0.00004198571,0.00003960298,0.0001422363,0.0002832589,0.007446057],"genre_scores_gemma":[0.8510544,0.0004358413,0.1447385,0.0004337943,0.00008875629,0.000165529,0.0001902171,0.0001682334,0.002724726],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00517846,"threshold_uncertainty_score":0.02738667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06913435806116296,"score_gpt":0.1823130635678727,"score_spread":0.1131787055067097,"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."}}