{"id":"W3017390413","doi":"","title":"Active Roll-outs in MDP with Irreversible Dynamics","year":2019,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Dynamics (music); Chemistry; Computer science; Physics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002852496,0.000414642,0.0004733387,0.0004014935,0.0001802782,0.0006597747,0.003404663,0.0003300953,0.00005396887],"category_scores_gemma":[0.0005258647,0.000424875,0.0001416955,0.0007618617,0.0001549134,0.0004513857,0.003319605,0.001238497,0.0001561037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000547985,"about_ca_system_score_gemma":0.0006575998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001073339,"about_ca_topic_score_gemma":0.001782175,"domain_scores_codex":[0.9946821,0.002544307,0.000500877,0.001056075,0.000695296,0.0005213688],"domain_scores_gemma":[0.9933142,0.00109692,0.0006643721,0.003480938,0.001291539,0.0001520376],"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":[0.00004541361,0.0005490963,0.0181658,0.0003876844,0.0002035652,0.00003738408,0.02022314,0.6452315,0.0001315004,0.2880932,0.0008551131,0.02607657],"study_design_scores_gemma":[0.0007606574,0.000001238077,0.005485735,0.001679369,0.00002048459,0.000008669671,0.0001228295,0.9853511,0.002374255,0.001435614,0.002192076,0.0005679097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01046503,0.00009881765,0.8724319,0.003986928,0.0003096286,0.0006105902,0.00001275521,0.0002455497,0.1118389],"genre_scores_gemma":[0.8396865,0.0001404202,0.1319537,0.0001302981,0.00001262099,0.00005174685,0.0002768837,0.00005345485,0.02769439],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8292215,"threshold_uncertainty_score":0.9998203,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009771959918208143,"score_gpt":0.2145248160499276,"score_spread":0.2047528561317195,"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."}}