{"id":"W6892661701","doi":"10.5281/zenodo.10626005","title":"Learning Conditional Policies for Crystal Design Using Offline Reinforcement Learning","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Reinforcement learning; Crystal (programming language); Online and offline; Key (lock); Offline learning; Trajectory","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":[0.001172431,0.001272119,0.001125499,0.0004978419,0.0003616942,0.0008664601,0.001641227,0.001420164,0.01164337],"category_scores_gemma":[0.005606125,0.0005564211,0.0006609402,0.000444363,0.0008201138,0.001114729,0.001158172,0.001832385,0.002675592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001238577,"about_ca_system_score_gemma":0.002239897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007390026,"about_ca_topic_score_gemma":0.01096957,"domain_scores_codex":[0.9995292,0.0001450213,0.00001629251,0.0001461245,0.00008615822,0.00007713147],"domain_scores_gemma":[0.9978848,0.001406115,0.0001057477,0.0002189785,0.0002504083,0.0001339002],"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":[0.0003013913,0.0001657381,0.001218326,0.0001284424,0.00004396823,0.00005402128,0.000031517,0.9036671,0.001071127,0.007932164,0.01075976,0.07462651],"study_design_scores_gemma":[0.00002423694,0.00001339059,0.00004152484,0.000005853637,0.000003013366,0.000003531954,0.000002410707,0.9962575,0.0003748923,0.002843285,0.0004278632,0.000002489239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06034849,0.000954094,0.9089147,0.000872194,0.0002865636,0.0002095311,0.002172468,0.01267347,0.01356839],"genre_scores_gemma":[0.7569523,0.0002616197,0.2247312,0.0006198559,0.0001118723,0.0005589435,0.00426071,0.001282431,0.01122095],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01164337,"threshold_uncertainty_score":0.03895098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05128356517961073,"score_gpt":0.2943236453669126,"score_spread":0.2430400801873019,"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."}}