{"id":"W3127407414","doi":"","title":"Planning from Pixels using Inverse Dynamics Models","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Task (project management); Heuristic; Computer science; Focus (optics); Artificial intelligence; Machine learning; Dynamics (music); Engineering; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001357152,0.0004255103,0.0004423329,0.0002390815,0.0002015085,0.0002840875,0.002736214,0.0003803059,0.0000176829],"category_scores_gemma":[0.00003972957,0.0005568563,0.0002247175,0.0005531763,0.00009774091,0.0008180449,0.004663016,0.001088653,0.00007821038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006252145,"about_ca_system_score_gemma":0.000309009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004590805,"about_ca_topic_score_gemma":0.0000131518,"domain_scores_codex":[0.9976293,0.0001398366,0.0002926375,0.001310636,0.0001858493,0.0004417175],"domain_scores_gemma":[0.9976785,0.0001285688,0.0004430972,0.001362873,0.0001210661,0.0002658674],"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":[0.00001177703,0.00001164194,0.001071552,0.00003244771,0.0001070608,0.0004007675,0.0005812463,0.9390701,0.00002273263,0.05856102,0.00008680721,0.00004283466],"study_design_scores_gemma":[0.0003144382,0.00002509063,0.00006278549,0.0001554,0.00008501946,0.000001734261,0.0001261492,0.9539625,0.00001846574,0.04466775,0.00005259225,0.0005280572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07053713,0.0000206661,0.9248285,0.00007556336,0.0007753475,0.0002187484,0.00001975671,0.0004383653,0.003085903],"genre_scores_gemma":[0.955574,0.00003212851,0.04351137,0.0002508172,0.0001046544,2.671004e-7,0.00007101514,0.00003565941,0.0004200245],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8850369,"threshold_uncertainty_score":0.9996883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1990412533670225,"score_gpt":0.212944628335268,"score_spread":0.01390337496824551,"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."}}