{"id":"W2914461813","doi":"10.1007/978-3-030-04735-1_3","title":"Emergent Policy Discovery for Visual Reinforcement Learning Through Tangled Program Graphs: A Tutorial","year":2019,"lang":"en","type":"book-chapter","venue":"Genetic and evolutionary computation","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Constructive; Task (project management); Computer science; A priori and a posteriori; Artificial intelligence; Human–computer interaction; Theoretical computer science; Machine learning; Programming language; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003918204,0.001007971,0.0007334547,0.0006658977,0.0002491886,0.001031606,0.0009416363,0.0009325796,0.00879219],"category_scores_gemma":[0.0009971942,0.0005757092,0.0009060308,0.0009162024,0.0007374763,0.001525252,0.001122107,0.002055846,0.001765101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008557168,"about_ca_system_score_gemma":0.0004071941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001101415,"about_ca_topic_score_gemma":0.001697943,"domain_scores_codex":[0.9998773,0.00002592696,0.00000805514,0.00003538257,0.00004299044,0.00001023589],"domain_scores_gemma":[0.9997496,0.0001763297,0.00001340903,0.00002006394,0.00002588669,0.0000146254],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004013885,0.0001064032,0.0002293065,0.000878151,0.00009474846,0.0001663785,0.0001596061,0.1746088,0.005326238,0.2823249,0.02835519,0.50771],"study_design_scores_gemma":[0.00001840614,0.00005122184,0.0002563164,0.0002247184,0.00002559115,0.0002121697,0.00003316261,0.4472931,0.002202905,0.4828451,0.06679603,0.00004129083],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002332754,0.01653755,0.9564329,0.0007305812,0.0003066504,0.00005222289,0.0001065424,0.0009222311,0.02257854],"genre_scores_gemma":[0.1225589,0.04029019,0.7801695,0.000679048,0.000833563,0.0004180367,0.0006077805,0.0008942941,0.0535487],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00879219,"threshold_uncertainty_score":0.02941281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01698892175237302,"score_gpt":0.2783094984559591,"score_spread":0.2613205767035861,"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."}}