{"id":"W4285805521","doi":"10.1145/3520304.3528766","title":"Benchmarking genetic programming in a multi-action reinforcement learning locomotion task","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Benchmarking; Reinforcement learning; Benchmark (surveying); Computer science; Task (project management); Scalability; Artificial intelligence; Action (physics); Genetic programming; Machine learning; 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":[0.000265156,0.0001518594,0.0001587464,0.0001926301,0.0007693314,0.00007529609,0.0004462726,0.0000372582,0.00001194007],"category_scores_gemma":[0.00001642147,0.0001513683,0.00005433123,0.0007236946,0.00008607671,0.0002972213,0.0006218235,0.0002788231,0.000001455461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001852946,"about_ca_system_score_gemma":0.00009581992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000773464,"about_ca_topic_score_gemma":0.000003019599,"domain_scores_codex":[0.998436,0.00005768625,0.0004468008,0.0004055122,0.0004183715,0.0002356324],"domain_scores_gemma":[0.9992055,0.00003869489,0.0003655377,0.00009935133,0.0002367649,0.00005414539],"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":[0.00001683957,0.0003250414,0.06866036,0.0001004206,0.00002034763,6.930933e-7,0.00207926,0.8136453,0.00417348,0.01318809,0.0002344075,0.09755576],"study_design_scores_gemma":[0.0003172694,0.0001037644,0.3021567,0.0000311975,0.000006096285,0.0000450222,0.0003825364,0.6933457,0.00003127367,0.002999573,0.0004632979,0.0001176041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3659953,0.0002281498,0.6323615,0.0005626159,0.0001678621,0.0005329078,0.000001173197,0.00006581545,0.00008465435],"genre_scores_gemma":[0.8952776,0.00005092099,0.1043746,0.00002579107,0.00003235416,0.000162539,0.00001005292,0.000007200264,0.0000589472],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5292822,"threshold_uncertainty_score":0.6172618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03241674665769873,"score_gpt":0.2598119153093554,"score_spread":0.2273951686516567,"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."}}