{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009566807,0.001005298,0.0008106774,0.0005026097,0.0003262205,0.0005678943,0.001538601,0.001140995,0.002131653],"category_scores_gemma":[0.002783816,0.000373996,0.0005702168,0.0005306724,0.0009344252,0.001565304,0.001495195,0.001834791,0.0003520093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009189646,"about_ca_system_score_gemma":0.0009551761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004340962,"about_ca_topic_score_gemma":0.004121705,"domain_scores_codex":[0.9996229,0.0001289252,0.00001866086,0.0001014041,0.00008313523,0.00004486161],"domain_scores_gemma":[0.9992923,0.0003844917,0.00007252643,0.00009414376,0.0001090107,0.00004756368],"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":[0.00005349863,0.00008207353,0.000432591,0.0000594217,0.00005112432,0.00006836246,0.00005066028,0.8918597,0.002058763,0.01261681,0.001364373,0.0913027],"study_design_scores_gemma":[0.000004024313,0.00001952438,0.00003019626,0.000002594044,0.000003728962,0.000006637477,0.000002772459,0.993061,0.0002844886,0.006373829,0.0002081712,0.000002932727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0146186,0.0002949291,0.9820781,0.0002498667,0.00006353096,0.00004804352,0.00003588589,0.0007672053,0.0018438],"genre_scores_gemma":[0.8536892,0.0003046255,0.1414875,0.0003190403,0.00006234944,0.0001885629,0.0001515293,0.0001405775,0.003656544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004340962,"threshold_uncertainty_score":0.008631408,"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."}}