{"id":"W4318712036","doi":"10.2139/ssrn.4329504","title":"Growspace: A Reinforcement Learning Environment for Plant Architecture","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Architecture and Computational Design","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Reinforcement learning; Architecture; Reinforcement; Computer science; Artificial intelligence; Computer architecture; Engineering; Geography; Structural 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":[0.0004882811,0.0001397118,0.0001155397,0.0001465173,0.0001884492,0.00002406121,0.0001271863,0.00004459116,0.00001364154],"category_scores_gemma":[0.00001273094,0.0001242804,0.00009910537,0.0001056696,0.0000122074,0.00003742614,0.00001890935,0.001020323,0.00006801625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003226017,"about_ca_system_score_gemma":0.0001477575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001742832,"about_ca_topic_score_gemma":0.00001016994,"domain_scores_codex":[0.9981626,0.0000224707,0.0001687354,0.0001104598,0.0002041666,0.001331568],"domain_scores_gemma":[0.9997462,0.00008259158,0.00003487517,0.00006552198,0.00000891833,0.00006187287],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000263133,0.000003172739,0.00002168619,0.00001216572,0.0001213599,0.000003204665,0.0002706519,0.9603615,0.0004939791,0.007662002,0.0005861868,0.03043774],"study_design_scores_gemma":[0.001683769,0.001149157,0.0004645479,0.00005224209,0.00007837419,0.0007567423,0.0009035268,0.3699053,0.0006115632,0.4442336,0.1794655,0.0006957029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02099472,0.0006879622,0.9769075,0.0003974492,0.0001734052,0.000203473,0.000002130749,0.0002462433,0.0003871091],"genre_scores_gemma":[0.9947486,0.00178421,0.0006644341,0.00004376969,0.0004781596,0.00004641279,0.00005559102,0.00005167548,0.002127183],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9762431,"threshold_uncertainty_score":0.5068008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005697605827617819,"score_gpt":0.1893931654341285,"score_spread":0.1836955596065106,"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."}}