{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001915514,0.001097895,0.001432207,0.0005977745,0.000468422,0.0008184762,0.002393352,0.001247664,0.003027274],"category_scores_gemma":[0.00659524,0.000561854,0.0005787475,0.0005375794,0.001274678,0.001913874,0.003545621,0.002513177,0.0006098616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001050109,"about_ca_system_score_gemma":0.001783227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00229305,"about_ca_topic_score_gemma":0.004294522,"domain_scores_codex":[0.99918,0.0003375208,0.00004966444,0.0001399326,0.0001915744,0.0001013504],"domain_scores_gemma":[0.9981706,0.0008669564,0.0002282888,0.0002657243,0.0002453681,0.0002230353],"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":[0.0002572779,0.0001794567,0.002000893,0.0001450249,0.00006687063,0.00009459167,0.0001980394,0.8118093,0.004173373,0.03771257,0.003322504,0.1400402],"study_design_scores_gemma":[0.00001529055,0.00003164534,0.00003571331,0.000006499654,0.000003406366,0.000008297106,0.000003896073,0.9926291,0.0002524092,0.006769596,0.0002391026,0.000005119036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01263699,0.0002065218,0.9847207,0.0002447306,0.00003938403,0.00006297068,0.00007338018,0.0008794212,0.001136006],"genre_scores_gemma":[0.7533304,0.0002223603,0.2415039,0.000367872,0.00006067599,0.0004737835,0.0002657098,0.0002441882,0.003531081],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003027274,"threshold_uncertainty_score":0.01013035,"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."}}