{"id":"W2020920737","doi":"10.1007/s12064-011-0142-z","title":"An information-theoretic approach to curiosity-driven reinforcement learning","year":2012,"lang":"en","type":"article","venue":"Theory in Biosciences","topic":"Statistical Mechanics and Entropy","field":"Physics and Astronomy","cited_by":179,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Curiosity; Randomness; Computer science; Artificial intelligence; Information theory; Machine learning; Mathematical optimization; Mathematics; Psychology","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":[0.0006067308,0.00008047721,0.00008574792,0.00008499606,0.0001321724,0.00006980269,0.0002143982,0.00001522466,0.000289444],"category_scores_gemma":[0.00002804869,0.00006359914,0.00001870643,0.000224373,0.00006664279,0.000493401,0.0000464739,0.00008825888,0.0001116615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001522316,"about_ca_system_score_gemma":0.00001523756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003182784,"about_ca_topic_score_gemma":1.028654e-7,"domain_scores_codex":[0.9992062,0.00007798571,0.0001532797,0.00009449001,0.000157829,0.0003102405],"domain_scores_gemma":[0.99962,0.00005897845,0.00004377524,0.0001107486,0.00001758762,0.0001488712],"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":[0.000007196297,0.00005072865,0.007001284,0.000002836549,0.00000189679,1.888578e-8,0.002583329,0.002486099,0.0001079926,0.9828262,0.00001336988,0.004919017],"study_design_scores_gemma":[0.0009495417,0.0007306207,0.01623194,0.00006921562,0.00003709838,0.000001782606,0.03500968,0.3915597,0.004053507,0.5421027,0.008137128,0.001117092],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2868705,0.000005509099,0.6507322,0.0000431821,0.000213534,0.0001870233,0.000005397798,0.00002441927,0.0619182],"genre_scores_gemma":[0.9971859,7.565417e-7,0.002507447,0.0001438043,0.00007478784,0.00002075572,0.00001333814,0.000002963272,0.00005024143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7103153,"threshold_uncertainty_score":0.3169209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01096080761445934,"score_gpt":0.2620237845681476,"score_spread":0.2510629769536882,"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."}}