{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00105317,0.001102331,0.001272292,0.000396817,0.0003563036,0.0008610418,0.002248178,0.00138461,0.00318662],"category_scores_gemma":[0.00294776,0.0007054457,0.0006609453,0.0004124748,0.001516224,0.001544262,0.001618799,0.002285352,0.0004470013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001125886,"about_ca_system_score_gemma":0.001258844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004136802,"about_ca_topic_score_gemma":0.005037995,"domain_scores_codex":[0.9996327,0.0001148106,0.00001626095,0.0001039112,0.00007800299,0.00005434084],"domain_scores_gemma":[0.9989875,0.0005523299,0.0001322951,0.0001350574,0.000101482,0.00009135472],"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":[0.0000673542,0.00006539272,0.0005933122,0.00006013296,0.00004075689,0.00008792899,0.00004183498,0.9443191,0.001385242,0.01564164,0.001323142,0.03637417],"study_design_scores_gemma":[0.000006510679,0.00001374954,0.00002363547,0.000003778218,0.000003512647,0.000006468891,0.000001861387,0.9947178,0.0002184858,0.004801048,0.000200796,0.000002533261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01750029,0.0002293278,0.9785401,0.0002323995,0.00004720758,0.00005618928,0.00004726191,0.0007743121,0.002572896],"genre_scores_gemma":[0.7535731,0.0002695549,0.240358,0.0003079632,0.00004811492,0.000290339,0.0002327676,0.0002233843,0.004696864],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004136802,"threshold_uncertainty_score":0.01066029,"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."}}