{"id":"W3199096322","doi":"10.3390/robotics10030105","title":"Reinforcement Learning for Pick and Place Operations in Robotics: A Survey","year":2021,"lang":"en","type":"article","venue":"Robotics","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Robotics; Task (project management); GRASP; Computer science; Field (mathematics); Imitation; Robot; Generalization; Strengths and weaknesses; Robot learning; Machine learning; Human–computer interaction; Engineering; Mobile robot; Psychology; Systems engineering; Software 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":[],"consensus_categories":[],"category_scores_codex":[0.0001976828,0.00009434671,0.000134342,0.00005830916,0.00008085999,0.00007238102,0.00003686995,0.00005793451,0.00002751082],"category_scores_gemma":[0.0002416666,0.0001113457,0.00002069565,0.0001518467,0.00000885976,0.00008420458,0.00002440108,0.000173983,0.00001017422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005248759,"about_ca_system_score_gemma":0.00002724281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002294779,"about_ca_topic_score_gemma":0.0007555237,"domain_scores_codex":[0.9993761,0.00004800355,0.0002043365,0.000122326,0.0000727649,0.0001764945],"domain_scores_gemma":[0.9996389,0.0001439866,0.00001276597,0.00009577453,0.00006032909,0.00004821843],"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":[0.000002450638,0.000005916051,0.007609107,0.00003746922,0.00001114268,0.000002488681,0.0002610656,0.9903557,0.0000957075,0.001280777,0.0001025953,0.0002355726],"study_design_scores_gemma":[0.0003760339,0.00001706547,0.01531746,0.00002676163,0.000006868705,0.000003503696,0.0001151082,0.9833957,0.00005593006,0.00001009063,0.0005466121,0.000128889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01428646,0.0002847667,0.984011,0.0002177478,0.0002150312,0.0001854574,4.256794e-7,0.0001144943,0.0006846348],"genre_scores_gemma":[0.9789342,0.00008788684,0.01899488,0.00004690064,0.00004023018,0.000009770998,0.0001018742,0.00002760139,0.001756621],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9650161,"threshold_uncertainty_score":0.4540548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03458840687386684,"score_gpt":0.2596132460538144,"score_spread":0.2250248391799475,"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."}}