{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001431369,0.0004443355,0.0003928292,0.0002770448,0.0003669481,0.000254662,0.0003363101,0.0002779633,0.00001393847],"category_scores_gemma":[0.00004177263,0.0004685286,0.0002212037,0.0001237636,0.0001023827,0.0004754616,0.0003562237,0.0002939008,0.00004621684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002597196,"about_ca_system_score_gemma":0.0005075937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002492273,"about_ca_topic_score_gemma":9.306257e-7,"domain_scores_codex":[0.9975078,0.00004239508,0.0006586681,0.0007195154,0.000631308,0.0004403864],"domain_scores_gemma":[0.9987252,0.000132364,0.0005196659,0.0002828731,0.0002457326,0.0000941806],"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":[0.00003767365,0.00001965861,0.00003126316,0.0001099752,0.0001291061,0.000002154387,0.0002655052,0.7816744,0.000007365796,0.2020314,0.00152223,0.01416917],"study_design_scores_gemma":[0.001003498,0.001726723,0.0004617901,0.0001313698,0.00008183141,0.00001893657,0.00001811042,0.8821999,0.000002291149,0.04873,0.06502155,0.0006039963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.0001359431,0.0006609578,0.9788247,0.0002005368,0.001695807,0.001818796,0.00000445728,0.0002516888,0.01640707],"genre_scores_gemma":[0.133003,0.001948506,0.3609985,0.0004851044,0.003978679,0.0004057387,0.002080097,0.0002498925,0.4968506],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6178263,"threshold_uncertainty_score":0.9997767,"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."}}