{"id":"W4393146598","doi":"10.1609/aaai.v38i21.30555","title":"Multi-world Model in Continual Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Elevator Systems and Control","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Psychology; Artificial intelligence; Social 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":[0.0003373608,0.0001830167,0.0002309358,0.0001817966,0.00005372866,0.0001382402,0.0003749052,0.00006299528,0.00005386971],"category_scores_gemma":[0.00007783907,0.0001432368,0.00008795059,0.0004224963,0.00007016867,0.0001755116,0.00005682169,0.0004392479,0.00007449463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007243321,"about_ca_system_score_gemma":0.00003559197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004136467,"about_ca_topic_score_gemma":0.00007290288,"domain_scores_codex":[0.9987276,0.000005639293,0.0005075819,0.0002288381,0.0002469639,0.0002833299],"domain_scores_gemma":[0.9996364,0.00003994645,0.00005951758,0.00009388757,0.0001229662,0.00004729663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000387258,0.00004093354,0.0003310116,0.0003243311,0.0000403509,0.000001705573,0.002918171,0.2706283,0.2035179,0.4902902,0.0002453779,0.03162294],"study_design_scores_gemma":[0.00002426898,0.00003061941,0.00002627191,0.0005560692,0.000007867544,7.945117e-7,0.0003964949,0.8899269,0.1055165,0.003138197,0.0002323625,0.0001437481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8507658,0.0008079326,0.05530728,0.001349246,0.002070471,0.001669943,0.00001004264,0.0009966288,0.08702263],"genre_scores_gemma":[0.9972667,0.00003422899,0.0002120715,0.00002474044,0.00005694755,0.00005017661,3.569859e-7,0.00002502418,0.002329755],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6192986,"threshold_uncertainty_score":0.5841028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05302181981312896,"score_gpt":0.2761287857989702,"score_spread":0.2231069659858412,"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."}}