{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004892426,0.0005460226,0.0004602255,0.0004592842,0.0003388983,0.000363921,0.002020121,0.000379701,0.00001143808],"category_scores_gemma":[0.0000544045,0.0006561067,0.0004794917,0.0004722781,0.0000924883,0.0004390616,0.003347677,0.001221015,0.00005573053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006511534,"about_ca_system_score_gemma":0.0005882789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003856498,"about_ca_topic_score_gemma":0.00000183236,"domain_scores_codex":[0.9969181,0.0001092392,0.0004195924,0.001557772,0.0002633648,0.0007319546],"domain_scores_gemma":[0.9977904,0.0001691162,0.0004163921,0.001122972,0.0002640098,0.0002371087],"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":[0.00004222946,0.00001436748,0.00001085002,0.0001358062,0.0001133006,0.00004365261,0.0002114071,0.6908047,0.00001072649,0.3083305,0.0001750209,0.0001073847],"study_design_scores_gemma":[0.0005932202,0.00017084,9.482919e-7,0.0002934011,0.0001617104,6.709436e-7,0.00003134312,0.938963,0.0002272452,0.05873052,0.0001997254,0.0006273616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003497701,0.0000361093,0.9910259,0.0000853773,0.0008737571,0.000890055,0.000006287105,0.0006614026,0.002923393],"genre_scores_gemma":[0.9585037,0.00002744783,0.03680184,0.0001264472,0.0001009746,0.00001305434,0.00003025439,0.0000588996,0.004337403],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9550059,"threshold_uncertainty_score":0.999589,"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."}}