{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001094018,0.0008782345,0.001069846,0.0004074863,0.0004279134,0.00075489,0.00214605,0.001253093,0.00229829],"category_scores_gemma":[0.003999881,0.0007177339,0.000554791,0.0004860128,0.001081266,0.001937082,0.002509964,0.001782369,0.0003634834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000939822,"about_ca_system_score_gemma":0.001501147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006550137,"about_ca_topic_score_gemma":0.006826748,"domain_scores_codex":[0.9995952,0.0001199854,0.00001841463,0.0001146324,0.00007839149,0.00007325618],"domain_scores_gemma":[0.998868,0.0006306227,0.0001130913,0.0001312378,0.0001401054,0.0001169103],"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":[0.0001081887,0.00008681275,0.001322844,0.00006355508,0.00003204701,0.00007861435,0.00007493197,0.9262824,0.001496917,0.009825586,0.001290675,0.05933737],"study_design_scores_gemma":[0.00001163368,0.00001777735,0.00003805982,0.000002971646,0.000002224211,0.000006965514,0.000003142296,0.9952395,0.0002182629,0.004276354,0.0001809209,0.000002157203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04778836,0.0002447009,0.9481751,0.0004983185,0.00004970012,0.00006077023,0.00008672336,0.0008272582,0.002269152],"genre_scores_gemma":[0.7587944,0.0001929707,0.2365999,0.0004387686,0.00004115021,0.0002119661,0.0002535528,0.0001314314,0.003335904],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006550137,"threshold_uncertainty_score":0.01302403,"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."}}