{"id":"W3100366369","doi":"10.1561/2200000071","title":"An Introduction to Deep Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"Foundations and Trends® in Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1251,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Deep learning; Generalization; Field (mathematics); Robotics; Machine learning; Robot; Mathematics","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":[0.0008229304,0.0008366553,0.0006438546,0.000698091,0.0002486498,0.001329299,0.0009674388,0.001460329,0.01211225],"category_scores_gemma":[0.00271042,0.0005086096,0.0007122797,0.001124497,0.0009260098,0.001546997,0.0009403393,0.003745896,0.003766999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001142233,"about_ca_system_score_gemma":0.0009410375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001815033,"about_ca_topic_score_gemma":0.001585789,"domain_scores_codex":[0.9995043,0.0001101602,0.00004437744,0.0001105007,0.0001904145,0.00004022126],"domain_scores_gemma":[0.9989842,0.0007060483,0.00004541449,0.00006993479,0.0001450637,0.00004943957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004500047,0.00009777046,0.0007419307,0.0008211383,0.00008142079,0.0001834002,0.0001511165,0.06748132,0.001948348,0.5343176,0.05989978,0.3342313],"study_design_scores_gemma":[0.0000191349,0.00007830806,0.0004354625,0.0004574441,0.00002347522,0.0002727931,0.00002479342,0.1092211,0.000908612,0.5734285,0.3150787,0.00005175703],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.001046136,0.03745495,0.9141513,0.005073014,0.001577671,0.00006732728,0.0007104234,0.0007703488,0.03914879],"genre_scores_gemma":[0.1627237,0.113413,0.630762,0.005939945,0.006087467,0.0007773435,0.001976637,0.000732322,0.07758758],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.01211225,"threshold_uncertainty_score":0.04051954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01379196626407731,"score_gpt":0.2905965508752665,"score_spread":0.2768045846111892,"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."}}