{"id":"W4401024442","doi":"10.24963/ijcai.2024/507","title":"Reasoning About Causal Knowledge in Nondeterministic Domains","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Regina","funders":"Youth Innovation Promotion Association; Tencent; National Key Research and Development Program of China; Youth Innovation Promotion Association of the Chinese Academy of Sciences; Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Operator (biology); Artificial intelligence","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":[0.0003214399,0.0001221247,0.0001190354,0.0002068862,0.00005335388,0.0004143257,0.0005566031,0.00005446143,0.00005980557],"category_scores_gemma":[0.00006080088,0.0001084462,0.00004148171,0.0005569549,0.0000329756,0.0003454406,0.0002757886,0.0002255319,0.0007734862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009882203,"about_ca_system_score_gemma":0.0001429571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001915846,"about_ca_topic_score_gemma":0.00002850068,"domain_scores_codex":[0.9988955,0.00004378551,0.0002335253,0.0003369655,0.0001733986,0.0003167728],"domain_scores_gemma":[0.999303,0.0002090732,0.00002121464,0.0003772452,0.00002128298,0.00006811778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001958216,0.00002818014,0.001323194,0.0001139074,0.00001955051,0.0004656885,0.002911411,0.06007881,0.0002134294,0.9132812,0.00262883,0.01893384],"study_design_scores_gemma":[0.0001095308,0.00005211328,0.001823147,0.000162406,0.000002975278,0.00002739509,0.00002319055,0.9823835,0.0000888842,0.000416318,0.0147547,0.0001557996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002710614,0.0002174402,0.872934,0.0001273344,0.0008301409,0.00007923062,1.819017e-7,0.000391781,0.1227093],"genre_scores_gemma":[0.9483964,0.00001383954,0.0372191,0.00008775131,0.00008513768,0.00000994485,0.000001321071,0.00001340311,0.01417312],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9456857,"threshold_uncertainty_score":0.9941857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01518561802750348,"score_gpt":0.2941535458412524,"score_spread":0.2789679278137489,"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."}}