{"id":"W2925216817","doi":"10.48550/arxiv.1903.09295","title":"DQN with model-based exploration: efficient learning on environments with sparse rewards","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","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":[0.0002453305,0.0004728897,0.000358497,0.0003008737,0.0002302696,0.0001830969,0.001394607,0.0002191868,0.00001491554],"category_scores_gemma":[0.0000156362,0.000442154,0.0001045524,0.0004102327,0.0001369191,0.0003125949,0.0007866609,0.001027185,0.0002566478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004938805,"about_ca_system_score_gemma":0.0003593204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001266928,"about_ca_topic_score_gemma":0.000001985158,"domain_scores_codex":[0.9974508,0.0001582154,0.00020123,0.001339803,0.0004032182,0.0004467385],"domain_scores_gemma":[0.9975382,0.00008587239,0.000451552,0.001676252,0.00008014704,0.0001679476],"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":[0.0001373943,0.00008097658,0.001625586,0.00004416461,0.00006278628,0.0001334343,0.0002900087,0.9879491,0.000006477475,0.009593773,0.00002187597,0.00005438118],"study_design_scores_gemma":[0.001029222,0.0006178865,0.0001809655,0.000271427,0.00006330882,0.000001542196,0.00005621008,0.9966331,0.000155255,0.0001026442,0.0003203279,0.0005681366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06541418,0.000004770893,0.9301715,0.00008163592,0.0001688003,0.0005008143,0.000001671465,0.0002170563,0.003439537],"genre_scores_gemma":[0.9850028,0.00001835644,0.008681974,0.0001211282,0.00002621987,0.000002886826,0.00003217825,0.00004294223,0.006071496],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9214895,"threshold_uncertainty_score":0.999803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06704040110681203,"score_gpt":0.1762259152804171,"score_spread":0.1091855141736051,"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."}}