{"id":"W7028572862","doi":"","title":"GenRL : multimodal-foundation world models for generalization in embodied agents","year":2024,"lang":"en","type":"article","venue":"Ghent University Academic Bibliography (Ghent University)","topic":"Military, Security, and Education Studies","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Vlaamse regering; Mitacs; Fonds Wetenschappelijk Onderzoek","keywords":"Embodied cognition; Generalization; Reinforcement learning; Foundation (evidence); Generative grammar; Representation (politics); Situated; Embodied agent; Natural language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00124493,0.0007843818,0.0008205579,0.0004501673,0.0003717042,0.001291935,0.001652814,0.001345234,0.004779235],"category_scores_gemma":[0.00460463,0.0006176788,0.001407319,0.0003937923,0.001354424,0.001961061,0.002443523,0.002311745,0.0008505252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001135187,"about_ca_system_score_gemma":0.00100161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004916328,"about_ca_topic_score_gemma":0.006903188,"domain_scores_codex":[0.9994609,0.0002338667,0.00002872077,0.0001276057,0.00009303337,0.00005590684],"domain_scores_gemma":[0.9987972,0.0007800966,0.0001150868,0.0001490156,0.00009574205,0.00006281745],"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":[0.00003083683,0.00002414992,0.0003339779,0.0000621241,0.00002928495,0.000066676,0.0001411892,0.8751751,0.0009141854,0.09422361,0.001360108,0.02763869],"study_design_scores_gemma":[0.000006370161,0.00001122596,0.00003778127,0.000009573878,0.000003967386,0.000008925402,0.000008359601,0.9587682,0.0001660589,0.04004808,0.0009259688,0.000005515924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004884933,0.0001262836,0.9919396,0.0002661445,0.00002196351,0.00002434617,0.000106673,0.000532637,0.002097452],"genre_scores_gemma":[0.5642434,0.0005149107,0.4249942,0.0004271838,0.00007862206,0.0005484124,0.0006367139,0.0005069349,0.00804959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004916328,"threshold_uncertainty_score":0.01598817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06045640778092552,"score_gpt":0.3077527237818308,"score_spread":0.2472963160009053,"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."}}