{"id":"W4402474348","doi":"10.1109/ccece59415.2024.10667224","title":"LLM4RL: Enhancing Reinforcement Learning with Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Human–computer interaction; Engineering","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":[0.000447237,0.0001865564,0.0001465697,0.0001647745,0.0001581669,0.0005758511,0.0005315801,0.00005193169,0.0001582197],"category_scores_gemma":[0.0000218018,0.0001403827,0.00005593807,0.0004656468,0.00001851918,0.001110843,0.0003188389,0.0003642338,0.0003385541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008418626,"about_ca_system_score_gemma":0.00009574617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003336991,"about_ca_topic_score_gemma":0.00001171896,"domain_scores_codex":[0.9983018,0.00003733014,0.0002530951,0.000409057,0.0005089442,0.000489768],"domain_scores_gemma":[0.9992573,0.00009417601,0.00004839497,0.0004558116,0.00004703816,0.00009729002],"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":[0.00000182589,0.000003880793,0.00001983545,0.00003993459,0.00002768138,0.00006116562,0.002935745,0.8254203,0.0003483194,0.1696953,0.0002048015,0.001241249],"study_design_scores_gemma":[0.000168888,0.0001604105,0.00000587091,0.000122134,0.000008464295,0.00002012232,0.0003569071,0.9902858,0.002321112,0.0001384372,0.006189696,0.0002222125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008803799,0.0001843214,0.923036,0.0002236093,0.0002009612,0.0001428727,1.002342e-7,0.001185931,0.07414585],"genre_scores_gemma":[0.9292291,0.00001830708,0.03514673,0.0002781134,0.00006568448,0.00001377091,0.000006083832,0.00002487867,0.03521733],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9283487,"threshold_uncertainty_score":0.5724642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01082649117583488,"score_gpt":0.246022324639814,"score_spread":0.2351958334639791,"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."}}