{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003658455,0.0002294942,0.0002813621,0.0001199285,0.0001225283,0.0001199282,0.002576696,0.0001917779,0.00008518474],"category_scores_gemma":[0.0001954768,0.0002051023,0.0002314728,0.0004239894,0.0001345558,0.0001815099,0.003201223,0.0007165323,0.00002983017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001068968,"about_ca_system_score_gemma":0.0001887609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004856085,"about_ca_topic_score_gemma":0.000003812042,"domain_scores_codex":[0.9983861,0.0002954299,0.0001922383,0.000703223,0.0001736775,0.0002493194],"domain_scores_gemma":[0.9967259,0.0004668021,0.0003840694,0.002176553,0.0001725559,0.0000741138],"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":[0.000008858336,0.00002994061,0.0005579105,0.00004397186,0.00005674881,0.00009171901,0.0001974528,0.8780669,0.00003813926,0.1202915,0.0005183404,0.00009853725],"study_design_scores_gemma":[0.0002337014,0.00007149538,0.001451544,0.0003184985,0.00004366462,0.000001945792,0.0001164427,0.9896573,0.001057283,0.00643486,0.0002603079,0.0003529161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1635971,0.00001608597,0.8263122,0.0001696152,0.0004589701,0.0001727541,0.000002045536,0.00008533999,0.009185782],"genre_scores_gemma":[0.9954562,0.00006959015,0.001708979,0.0001385335,0.00002485831,5.63934e-7,0.000005010143,0.0000112136,0.002585095],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.831859,"threshold_uncertainty_score":0.836383,"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."}}