{"id":"W3176022961","doi":"10.1145/3449639.3459348","title":"On the impact of tangled program graph marking schemes under the atari reinforcement learning benchmark","year":2021,"lang":"en","type":"article","venue":"Proceedings of the Genetic and Evolutionary Computation Conference","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Reinforcement learning; Benchmark (surveying); Graph; Adaptation (eye); Heuristic; Scheme (mathematics); Theoretical computer science; Modularity (biology); Artificial intelligence; Node (physics); Machine learning; Engineering; Mathematics","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":[0.0003098927,0.0001571557,0.0001546348,0.00005633801,0.000414934,0.0001458754,0.0006484287,0.00004595846,0.00002765809],"category_scores_gemma":[0.0001727133,0.00008685522,0.0001180328,0.0005348742,0.000247476,0.0001536137,0.0004803353,0.0002406144,0.000001524164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004791707,"about_ca_system_score_gemma":0.0001996233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002050188,"about_ca_topic_score_gemma":2.869891e-7,"domain_scores_codex":[0.9986526,0.00005040587,0.000351429,0.0002523281,0.0004826788,0.0002105274],"domain_scores_gemma":[0.9984017,0.000285612,0.0004277092,0.0001791579,0.0006672573,0.00003858799],"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":[0.00001316077,0.00003198794,0.006647157,0.00003553395,0.00008193805,1.821034e-7,0.0006361585,0.8923682,0.0007604103,0.09556028,0.0004590458,0.003405926],"study_design_scores_gemma":[0.0001920514,0.0002451935,0.09381811,0.0001308011,0.00001941763,0.00001563612,0.0004044256,0.8874738,0.000450463,0.0170785,0.00006346132,0.0001080976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.485411,0.0002600701,0.5096315,0.001556017,0.0001200874,0.0004944096,6.379188e-7,0.00004950351,0.002476769],"genre_scores_gemma":[0.989108,0.00007118179,0.01052345,0.00006554956,0.00001910543,0.00002078977,0.000003023506,0.000006317171,0.0001825825],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.503697,"threshold_uncertainty_score":0.3541853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0203845929356071,"score_gpt":0.258709105662269,"score_spread":0.2383245127266619,"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."}}