{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001791485,0.0006706649,0.0008712598,0.0007377585,0.0003877739,0.0006827957,0.001280685,0.00120477,0.001590975],"category_scores_gemma":[0.005678908,0.0003510334,0.0004348568,0.000473179,0.0009230227,0.001002661,0.001131763,0.001300584,0.0002448995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001575482,"about_ca_system_score_gemma":0.001009533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002906424,"about_ca_topic_score_gemma":0.002746406,"domain_scores_codex":[0.9994699,0.0001794582,0.0000282833,0.000108453,0.0001686125,0.00004537127],"domain_scores_gemma":[0.9983647,0.0009832468,0.0001859211,0.0001127925,0.0002606433,0.00009272525],"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":[0.00007628121,0.00008469723,0.001183184,0.00005023905,0.00004287738,0.00005467124,0.00005030574,0.9143208,0.002575255,0.01218564,0.0008320245,0.06854406],"study_design_scores_gemma":[0.00000650185,0.00002532487,0.00006151143,0.000002577189,0.000002445564,0.000008829235,0.000001958544,0.9969296,0.0003266914,0.002492996,0.0001391411,0.00000244544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05265215,0.0002688902,0.9440467,0.0002392056,0.00004959806,0.00007083257,0.00004144796,0.0004010516,0.002230203],"genre_scores_gemma":[0.7765415,0.0001165428,0.220316,0.0001416636,0.00003849992,0.0002084436,0.00009548179,0.0001085445,0.002433294],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002906424,"threshold_uncertainty_score":0.01143098,"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."}}