{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000251821,0.000271675,0.0002592153,0.0003787137,0.0002781207,0.0004686811,0.001070813,0.0001559834,0.00001041647],"category_scores_gemma":[0.00008703509,0.0003343899,0.00009418481,0.0006540166,0.000107687,0.00126638,0.00242306,0.0004264915,0.00006216811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001767541,"about_ca_system_score_gemma":0.0001559759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002712118,"about_ca_topic_score_gemma":0.00002454142,"domain_scores_codex":[0.9979982,0.0001703882,0.0002809903,0.001035362,0.0001636783,0.0003513789],"domain_scores_gemma":[0.9980617,0.0001481572,0.000409003,0.001049873,0.0001869877,0.0001443068],"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":[0.00001043914,0.00001397775,0.003835663,0.00006226941,0.00006426004,0.0001055773,0.0004820387,0.9769982,0.00006818855,0.01818302,0.0000879368,0.00008846324],"study_design_scores_gemma":[0.0003171102,0.00002967918,0.00115798,0.00007668971,0.00005231463,0.000002345004,0.0001095363,0.9613213,0.0001526257,0.03636658,0.00009855518,0.0003152861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1042276,0.00001418864,0.893838,0.0001990487,0.000651974,0.0003805582,0.000009648213,0.0004116441,0.000267284],"genre_scores_gemma":[0.9863017,0.0003679514,0.009187092,0.00003260005,0.00005502038,0.000002232964,0.00004267445,0.00003218496,0.003978502],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8846509,"threshold_uncertainty_score":0.9999108,"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."}}