{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002623383,0.0008042005,0.001524752,0.0008786547,0.0006966564,0.001829383,0.003084831,0.001673426,0.005531598],"category_scores_gemma":[0.01244316,0.0005139334,0.0008949401,0.000836529,0.002998382,0.002889815,0.002284097,0.002515674,0.0003009857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002244051,"about_ca_system_score_gemma":0.002356554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003303235,"about_ca_topic_score_gemma":0.003577855,"domain_scores_codex":[0.9981533,0.001025189,0.00007809111,0.0002541991,0.0003552217,0.0001340989],"domain_scores_gemma":[0.9931042,0.005198624,0.0004475199,0.0003261664,0.0005597476,0.0003638172],"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":[0.00007158568,0.0001068064,0.0008229602,0.000137232,0.000126321,0.00007275537,0.0002349017,0.4005397,0.0006122543,0.5718309,0.001662541,0.02378209],"study_design_scores_gemma":[0.00002100595,0.00004357514,0.0001286651,0.00001477275,0.00001423207,0.00001478335,0.00001758568,0.6324174,0.0001097983,0.3666764,0.0005255972,0.00001623793],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02510155,0.0005208301,0.9564503,0.002696506,0.0001261034,0.00008581424,0.0001538755,0.0001471666,0.01471774],"genre_scores_gemma":[0.9015924,0.0004651312,0.09113109,0.0005231526,0.000173133,0.0002713151,0.00009403757,0.0000662087,0.005683441],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005531598,"threshold_uncertainty_score":0.0185051,"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."}}