{"id":"W4392308684","doi":"10.1039/d4dd00024b","title":"Learning conditional policies for crystal design using offline reinforcement learning","year":2024,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Crystallization and Solubility Studies","field":"Materials Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Institut de Valorisation des Données; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; Social psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001842237,0.001045971,0.001291273,0.000446593,0.0004014225,0.0008412311,0.001480868,0.001397457,0.00505185],"category_scores_gemma":[0.00946577,0.0004929749,0.0004402609,0.000402666,0.001390843,0.001163481,0.001154495,0.002279979,0.0007246445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001341597,"about_ca_system_score_gemma":0.002610799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007605217,"about_ca_topic_score_gemma":0.009721491,"domain_scores_codex":[0.9994953,0.0002068925,0.00001877056,0.00009429696,0.00009768764,0.0000869865],"domain_scores_gemma":[0.9934363,0.005374441,0.0002107644,0.0002891838,0.0004423068,0.0002468853],"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":[0.0001570441,0.0001073525,0.0007229703,0.00005493939,0.00002101198,0.00003471321,0.00002896411,0.9707416,0.0004242898,0.005274071,0.001218429,0.02121467],"study_design_scores_gemma":[0.00001561644,0.00001285403,0.00002836632,0.000002920964,0.000001829877,0.000001960111,0.000002403498,0.9975085,0.0001128486,0.002244695,0.00006653976,0.000001427877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1075665,0.0007005678,0.8815616,0.0009306374,0.0001533995,0.0001549012,0.0002400495,0.00218634,0.006505969],"genre_scores_gemma":[0.9171067,0.0001341741,0.07871891,0.0003882198,0.00005002516,0.0002663431,0.0003638302,0.0001801154,0.002791659],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007605217,"threshold_uncertainty_score":0.01690012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04786053706346439,"score_gpt":0.3042265212792106,"score_spread":0.2563659842157462,"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."}}