{"id":"W4382334265","doi":"10.48550/arxiv.2306.14808","title":"Maximum State Entropy Exploration using Predecessor and Successor Representations","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Canada Excellence Research Chairs, Government of Canada; Canadian Institute for Advanced Research","keywords":"Successor cardinal; Computer science; Entropy (arrow of time); Exploratory research; Artificial intelligence; Machine learning; Mathematics; Sociology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001697982,0.0008246986,0.001250944,0.0009543679,0.000455475,0.001027895,0.001332278,0.001219859,0.001857081],"category_scores_gemma":[0.007482238,0.0006054086,0.0008155175,0.0006630174,0.001499257,0.002424193,0.001521595,0.001691709,0.0002707227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001294766,"about_ca_system_score_gemma":0.001401564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002843074,"about_ca_topic_score_gemma":0.003541603,"domain_scores_codex":[0.9992629,0.0003085999,0.00004141542,0.0001717498,0.0001241496,0.00009117334],"domain_scores_gemma":[0.9959022,0.003006849,0.0003212828,0.0003478543,0.0002508951,0.0001709227],"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":[0.0001659299,0.00006872963,0.001865209,0.0000533529,0.00003974482,0.00005503958,0.00008847323,0.944113,0.000801917,0.01574715,0.0006517895,0.0363497],"study_design_scores_gemma":[0.000009374507,0.00002615688,0.0001000622,0.000006352546,0.000003938684,0.000007418349,0.000003830164,0.9877146,0.0002124134,0.01182674,0.00008465023,0.000004536987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1702753,0.0004937479,0.8238757,0.0006016215,0.00003667467,0.00008559494,0.0002241868,0.000741008,0.003666097],"genre_scores_gemma":[0.9481664,0.0001371853,0.04955388,0.0001093612,0.00002293024,0.0001404463,0.000230781,0.00005657764,0.001582493],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002843074,"threshold_uncertainty_score":0.009394228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1769339594121895,"score_gpt":0.2438982565846883,"score_spread":0.0669642971724988,"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."}}