{"id":"W4399116101","doi":"10.48550/arxiv.2405.16899","title":"Partial Models for Building Adaptive Model-Based Reinforcement Learning Agents","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; Social psychology","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":[0.001001487,0.0009434466,0.001145203,0.000454424,0.0004428787,0.001138904,0.001607063,0.001261079,0.002540833],"category_scores_gemma":[0.004695378,0.0008785831,0.0009731135,0.0003184968,0.00145325,0.001892154,0.002306702,0.002091653,0.0005346827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001166766,"about_ca_system_score_gemma":0.001244121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004754286,"about_ca_topic_score_gemma":0.00644,"domain_scores_codex":[0.9994836,0.000184939,0.00003472165,0.0001109857,0.0001269561,0.00005877582],"domain_scores_gemma":[0.9984742,0.0007771968,0.0001622118,0.0002465085,0.0002082347,0.0001316975],"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":[0.00002682973,0.00001427526,0.0003188573,0.00002922099,0.00002752306,0.00003093872,0.00005536904,0.9740397,0.0006091882,0.01660013,0.0003243725,0.007923584],"study_design_scores_gemma":[0.00000429385,0.00001311529,0.00001787721,0.000003437157,0.000003979369,0.000005176176,0.00000349252,0.9901932,0.000151676,0.009322261,0.0002785282,0.00000288766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02188157,0.0001854609,0.9748383,0.0003126096,0.00003274007,0.00005140339,0.00009373522,0.0007974845,0.001806655],"genre_scores_gemma":[0.8016121,0.0002700926,0.1935424,0.0002963351,0.00003797395,0.0004019808,0.0002632388,0.0001730554,0.003403008],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004754286,"threshold_uncertainty_score":0.009453177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.129754582277124,"score_gpt":0.2299798508596424,"score_spread":0.1002252685825184,"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."}}