{"id":"W4401023575","doi":"10.24963/ijcai.2024/723","title":"BILE: An Effective Behavior-based Latent Exploration Scheme for Deep Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Science North","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Centre Scientifique et Technique du Bâtiment; National Natural Science Foundation of China","keywords":"Inference; Computer science; Fake news; Artificial intelligence; Internet privacy","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":[0.0006549728,0.00006871359,0.00006215641,0.00009346175,0.0003508008,0.0002753164,0.0000618859,0.00005778526,0.0007041118],"category_scores_gemma":[0.0001615055,0.00005758493,0.00004930168,0.0001895348,0.00003300462,0.001187308,0.000007163902,0.00007177429,0.0001063208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000182027,"about_ca_system_score_gemma":0.0001031168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002588771,"about_ca_topic_score_gemma":0.0002083774,"domain_scores_codex":[0.9992509,0.0000581011,0.0001444303,0.0001070191,0.0002507151,0.0001887796],"domain_scores_gemma":[0.999629,0.00006690181,0.00003259841,0.0000645111,0.00009081536,0.0001161565],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001340632,0.0001490081,0.0006096687,0.0001649166,0.00003542859,0.000003723893,0.1769529,0.03877643,0.002416095,0.3406264,0.003185118,0.4369463],"study_design_scores_gemma":[0.0009303035,0.001300895,0.001660666,0.00008678417,0.00005326087,3.99824e-7,0.03226428,0.793792,0.004847955,0.0004792492,0.1641445,0.0004397026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2913911,0.00006892383,0.6540885,0.001679606,0.0008941483,0.00316076,0.000002288495,0.0009960819,0.04771864],"genre_scores_gemma":[0.9964967,0.00001017297,0.0009463871,0.0002101976,0.0001059059,0.0001046214,0.00005834294,0.000007641906,0.002059987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7550156,"threshold_uncertainty_score":0.7709531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05678271281901473,"score_gpt":0.3693819795439233,"score_spread":0.3125992667249086,"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."}}