{"id":"W4393160540","doi":"10.1609/aaai.v38i15.29571","title":"A Transfer Approach Using Graph Neural Networks in Deep Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Research in Systems and Signal Processing","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; University of Alberta; Alberta Machine Intelligence Institute; Compute Canada; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Transfer of learning; Artificial intelligence; Graph; Artificial neural network; Reinforcement; Theoretical computer science; Psychology; Social psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.000553377,0.000214358,0.0002469528,0.0002130288,0.0001210711,0.0002140642,0.0004110488,0.00009805767,0.00003126695],"category_scores_gemma":[0.00006959026,0.0001617058,0.0001051242,0.000854987,0.0001459377,0.0004207447,0.00005522603,0.0007819372,0.00000438686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008389005,"about_ca_system_score_gemma":0.00002512322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002499695,"about_ca_topic_score_gemma":0.000003322715,"domain_scores_codex":[0.9983792,0.00001662886,0.0005208731,0.0002905637,0.0003630744,0.000429648],"domain_scores_gemma":[0.9996154,0.0000607606,0.00003459468,0.00008409744,0.0001347114,0.00007045033],"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":[0.00002562786,0.0000142117,0.00003638708,0.0003335505,0.00001471943,0.000001395826,0.000836101,0.8945118,0.02789674,0.04298081,0.00000303963,0.03334558],"study_design_scores_gemma":[0.0000160117,0.00004567559,0.000003699578,0.0005679446,0.000007866432,0.000006220269,0.0009743529,0.9586887,0.03452202,0.004973798,0.00002381231,0.0001699223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1557525,0.0007465495,0.8316255,0.00009165051,0.0004671561,0.0005318283,6.842871e-7,0.0002213939,0.01056272],"genre_scores_gemma":[0.9993617,0.00009173341,0.0003209876,0.00001365374,0.00009461978,0.00002970119,5.856238e-7,0.00003339835,0.00005364995],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8436092,"threshold_uncertainty_score":0.6594171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07550551617635658,"score_gpt":0.2994715040283441,"score_spread":0.2239659878519875,"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."}}