{"id":"W2909958171","doi":"10.1007/978-3-030-10546-4_2","title":"Reinforcement Learning and Deep Reinforcement Learning","year":2019,"lang":"en","type":"book-chapter","venue":"Springer briefs in electrical and computer engineering","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Reinforcement; Artificial intelligence; Deep learning; Q-learning; Computer science; Psychology; Social 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":[0.0003973241,0.0007325314,0.0007712549,0.0006527505,0.0001482366,0.0004093051,0.0006030983,0.0003954042,0.00002910112],"category_scores_gemma":[0.00004840068,0.0007978489,0.0001320704,0.0002007835,0.00004744754,0.0003416578,0.00128515,0.002171719,0.00004923774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002671893,"about_ca_system_score_gemma":0.00007456013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001391881,"about_ca_topic_score_gemma":8.93066e-7,"domain_scores_codex":[0.996617,0.00002951989,0.0008215031,0.001005784,0.0006438792,0.0008823204],"domain_scores_gemma":[0.9986823,0.0002659847,0.0002880164,0.0004439042,0.00007480064,0.0002449836],"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":[0.000007089408,0.000004116095,0.00023008,0.0001398681,0.00007468888,0.00004529079,0.0001737246,0.8677719,0.00001996953,0.1078433,0.00001728527,0.0236727],"study_design_scores_gemma":[0.0005473612,0.0004582969,0.0002554824,0.0003688817,0.00002226423,0.00004832862,0.00000109696,0.9232041,0.00002369382,0.0001366735,0.07411368,0.0008201709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00009352972,0.00153566,0.9755058,0.00006572286,0.0004161577,0.0004313852,5.009786e-8,0.0003683068,0.02158334],"genre_scores_gemma":[0.5613054,0.01013317,0.06890713,0.0009701056,0.001615974,0.00008487875,0.00006679189,0.0005840155,0.3563325],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9065987,"threshold_uncertainty_score":0.9994472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006681597574720062,"score_gpt":0.1933348836968352,"score_spread":0.1866532861221151,"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."}}