{"id":"W6966484415","doi":"10.48448/rq6a-7z95","title":"A Transfer Approach Using Graph Neural Networks in Deep Reinforcement Learning | VIDEO","year":2024,"lang":"en","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Generalization; Transfer of learning; Reinforcement learning; Embedding; Artificial neural network; Graph; Turret; Robot","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":[0.0006212441,0.000799266,0.0005139396,0.0003986381,0.0002911049,0.0005482715,0.001141694,0.0009257324,0.002666065],"category_scores_gemma":[0.001969395,0.0002590886,0.0004161879,0.0004381201,0.0007606779,0.001396249,0.001328135,0.001499195,0.0004284626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008591093,"about_ca_system_score_gemma":0.0007689031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00665645,"about_ca_topic_score_gemma":0.005591553,"domain_scores_codex":[0.9997504,0.00007527362,0.000009910467,0.00007715759,0.00005587995,0.00003134268],"domain_scores_gemma":[0.9996377,0.0001703177,0.00004505208,0.0000603086,0.00005424046,0.00003238552],"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":[0.0001106569,0.0001291127,0.0005981503,0.00008948153,0.00005360468,0.0001084461,0.00007027292,0.7621059,0.004450543,0.02054304,0.004279795,0.2074609],"study_design_scores_gemma":[0.000004239871,0.00001453006,0.00004593213,0.000002749557,0.000002480216,0.00000681916,0.000003081872,0.9906566,0.0005927819,0.00825107,0.0004168382,0.000002858405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.02214336,0.000433502,0.9716684,0.000428047,0.00008794128,0.00005131076,0.00009258134,0.001586924,0.003507964],"genre_scores_gemma":[0.8446484,0.0003569993,0.1481734,0.000263854,0.00005713383,0.0001304051,0.0002712682,0.0002126651,0.005885971],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.00665645,"threshold_uncertainty_score":0.01323539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04927660240623646,"score_gpt":0.3020640855486687,"score_spread":0.2527874831424323,"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."}}