{"id":"W3214099510","doi":"","title":"Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Reinforcement learning; Construct (python library); Brick; Computer science; Object (grammar); Action (physics); Combinatorial explosion; Artificial intelligence; Space (punctuation); Theoretical computer science; Mathematics; Engineering; Programming language; Civil 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":[0.0001465252,0.0002002713,0.0001980111,0.0001054831,0.000337059,0.0001726369,0.0005623675,0.00009326302,0.00008680256],"category_scores_gemma":[0.00005795007,0.0002249207,0.00007458006,0.001046823,0.0001210738,0.0007194343,0.0003439761,0.0003465692,0.0001032044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001996207,"about_ca_system_score_gemma":0.0001650643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003194637,"about_ca_topic_score_gemma":0.000003713694,"domain_scores_codex":[0.9985104,0.0001271419,0.0001829905,0.0005937681,0.0001960914,0.0003895712],"domain_scores_gemma":[0.9987508,0.00009153453,0.000202603,0.0005453263,0.0002545323,0.0001552065],"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":[0.00001858934,0.00001917097,0.004809023,0.000009170848,0.00004715269,0.0001751299,0.0001107627,0.8031628,0.000110365,0.1911162,0.0001495205,0.0002721671],"study_design_scores_gemma":[0.001636941,0.000279341,0.000248599,0.00003007409,0.00004198401,0.00005580225,0.0003041198,0.9889662,0.001343954,0.0007871611,0.005921342,0.0003844294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03115051,0.00001859105,0.9578028,0.00006487149,0.000554364,0.0001084511,1.726895e-7,0.0002353437,0.01006484],"genre_scores_gemma":[0.9918407,0.00005118789,0.003133371,0.00008327935,0.00004662426,3.981425e-7,0.00001591883,0.0000139762,0.004814507],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9606902,"threshold_uncertainty_score":0.9172001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02086317014870699,"score_gpt":0.1593740189104158,"score_spread":0.1385108487617088,"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."}}