{"id":"W2951553872","doi":"","title":"SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Robotics; Range (aeronautics); Simple (philosophy); Linear-quadratic regulator; Offline learning; Quadratic equation; Image (mathematics); Machine learning; Control (management); Robot; Online learning; Mathematics; Engineering","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":[0.0003622911,0.0004359431,0.0003844907,0.0003898682,0.000556014,0.0003099581,0.002285217,0.0003721213,0.00004403658],"category_scores_gemma":[0.0002013201,0.0005289992,0.0003580594,0.0004497426,0.0001596376,0.0004346264,0.00165815,0.0007455627,0.00004799826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003683252,"about_ca_system_score_gemma":0.0004463182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003208351,"about_ca_topic_score_gemma":0.00001274759,"domain_scores_codex":[0.9973418,0.000128539,0.000397984,0.001321202,0.0002172394,0.0005932099],"domain_scores_gemma":[0.9967065,0.0002038373,0.0006136975,0.001749098,0.0005176009,0.0002092746],"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":[0.00003620032,0.00001447711,0.0004904405,0.00009265749,0.00009481391,0.00001360789,0.0002770986,0.9627579,0.00002190043,0.03575049,0.0003071303,0.0001432291],"study_design_scores_gemma":[0.0008377756,0.0001469504,0.00006832611,0.00006384507,0.0001036921,9.1961e-7,0.00004269229,0.9868873,0.0003048441,0.01048078,0.0005245291,0.0005383337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003021094,0.00001113508,0.9924273,0.0000886042,0.0006841532,0.000871775,0.000004288506,0.000470113,0.002421573],"genre_scores_gemma":[0.9314914,0.00002060327,0.06296216,0.0001490873,0.0001136201,0.000008191168,0.0001396283,0.00003995038,0.00507541],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9294651,"threshold_uncertainty_score":0.9997162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0705683000237207,"score_gpt":0.2240496447580726,"score_spread":0.1534813447343519,"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."}}