{"id":"W2918549499","doi":"10.1145/3319619.3321956","title":"Novelty search for deep reinforcement learning policy network weights by action sequence edit metric distance","year":2019,"lang":"en","type":"preprint","venue":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Neuroevolution; Computer science; Novelty; Metric (unit); Benchmark (surveying); Deep learning; Machine learning; Action (physics); Artificial neural network","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":[0.0004961826,0.0004121755,0.0004775243,0.0002851379,0.0005577187,0.0003518965,0.001325422,0.0002579899,0.000004799577],"category_scores_gemma":[0.0001286769,0.0003732223,0.0001601746,0.0007543305,0.0001901315,0.0004070686,0.00166338,0.000691253,0.000005611929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004200783,"about_ca_system_score_gemma":0.0004870877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007599423,"about_ca_topic_score_gemma":7.110729e-7,"domain_scores_codex":[0.9969352,0.00006104801,0.0007569444,0.0008164805,0.0008967895,0.0005335525],"domain_scores_gemma":[0.9969152,0.0002458722,0.001081103,0.0002789135,0.001355951,0.0001229586],"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":[0.00002588736,0.00002107743,0.005102526,0.0005293107,0.0000541063,4.717119e-8,0.0003712396,0.9686683,0.0002545618,0.01964583,0.001467624,0.003859505],"study_design_scores_gemma":[0.000413458,0.0001945256,0.01256181,0.0003812916,0.00003962315,0.000009014224,0.00007914125,0.9748709,0.0002325179,0.009839672,0.001006245,0.0003718388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01602587,0.0005798574,0.9794462,0.0008713523,0.001136015,0.00136077,0.000006551954,0.0001173471,0.0004560411],"genre_scores_gemma":[0.947812,0.0004780988,0.05051413,0.00006724621,0.000373351,0.00006929907,0.00008666609,0.00002505628,0.0005741459],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9317861,"threshold_uncertainty_score":0.999872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04233092629446205,"score_gpt":0.2901398948073653,"score_spread":0.2478089685129032,"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."}}