{"id":"W4414360785","doi":"10.24963/ijcai.2024/1181","title":"The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Elevator Systems and Control","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Key (lock); Action (physics); Reinforcement learning; Taxonomy (biology); Natural language","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":[0.0001507758,0.00005699004,0.00007228308,0.00002387404,0.00004545886,0.00006993272,0.00003696476,0.00002269883,0.00005576644],"category_scores_gemma":[0.00001472606,0.00003298153,0.00002189914,0.00007323513,0.000008798488,0.00004452288,0.000009579654,0.0000914526,0.000009104609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009772248,"about_ca_system_score_gemma":0.000007191786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003901864,"about_ca_topic_score_gemma":0.00001787533,"domain_scores_codex":[0.9996421,0.000008259318,0.0001339208,0.00005266829,0.00006639848,0.00009668573],"domain_scores_gemma":[0.9998149,0.00007691651,0.000007662032,0.00006282959,0.00001790357,0.00001974098],"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":[0.00004640468,0.00002152485,0.01879192,0.002597199,0.00188085,0.00005145638,0.006617845,0.2701184,0.1396239,0.1765965,0.0648114,0.3188426],"study_design_scores_gemma":[0.00009074582,0.0000302426,0.0002236141,0.00009338074,0.000008770551,0.000003127253,0.0005009739,0.9478844,0.0009577655,0.00001744044,0.05013189,0.00005769359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5631671,0.06925213,0.05872574,0.0003531764,0.001661815,0.000544159,0.000002364231,0.001667982,0.3046255],"genre_scores_gemma":[0.9955131,0.0001249463,0.000020373,0.000003494467,0.00003574393,0.000007329105,8.373347e-7,0.00001043802,0.004283675],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.677766,"threshold_uncertainty_score":0.1344948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003285814898221388,"score_gpt":0.1797980436110342,"score_spread":0.1765122287128129,"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."}}