{"id":"W4405778651","doi":"10.1109/iros58592.2024.10802721","title":"Guiding Reinforcement Learning with Incomplete System Dynamics","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Honeywell (Canada); University of British Columbia","funders":"","keywords":"Reinforcement learning; Computer science; Dynamics (music); Artificial intelligence; Human–computer interaction; Psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00125968,0.0008998879,0.0008908262,0.0002996689,0.0003146296,0.000539274,0.0008880656,0.0006585458,0.00100113],"category_scores_gemma":[0.004312738,0.0004691287,0.0003217674,0.0001740489,0.001076964,0.0008762794,0.001006221,0.0012692,0.0001830837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007419862,"about_ca_system_score_gemma":0.00135948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005139455,"about_ca_topic_score_gemma":0.004308962,"domain_scores_codex":[0.9996307,0.0001226574,0.00001900796,0.00008466796,0.00008584592,0.000057153],"domain_scores_gemma":[0.9978739,0.001436709,0.0002304146,0.000177339,0.0001880309,0.00009356008],"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":[0.00004167251,0.00002541597,0.0002499802,0.00003036076,0.00001521136,0.000031826,0.00003722625,0.9805419,0.001278106,0.003576277,0.0002214947,0.01395051],"study_design_scores_gemma":[0.000006116909,0.00001226365,0.0000231643,0.000001762087,0.000001958456,0.000003541587,0.000001576597,0.9981251,0.0002741698,0.001468446,0.00008027268,0.000001534891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02795012,0.00007671185,0.9705117,0.0001042382,0.0000162433,0.00002628278,0.0000159161,0.0004223319,0.0008763766],"genre_scores_gemma":[0.9335965,0.00006229444,0.06489045,0.00007612412,0.00002017642,0.00008323295,0.00003854362,0.00005626696,0.001176491],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005139455,"threshold_uncertainty_score":0.0102191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01837415516122789,"score_gpt":0.2285996606694019,"score_spread":0.210225505508174,"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."}}