{"id":"W7134200277","doi":"10.1109/bigdata66926.2025.11402252","title":"Goal-Conditioned Reinforcement Learning for Data-Driven Maritime Navigation","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Reinforcement learning; Control (management); Action (physics); Field (mathematics); Stability (learning theory)","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":[0.001002675,0.0005387677,0.0008379834,0.0002314444,0.0002760308,0.0004924994,0.001135989,0.000679849,0.001980551],"category_scores_gemma":[0.003497958,0.0003374867,0.0003420457,0.0002564354,0.0007991148,0.0006343228,0.001247021,0.001502528,0.0002602857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007160925,"about_ca_system_score_gemma":0.001217094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006798736,"about_ca_topic_score_gemma":0.006074836,"domain_scores_codex":[0.9996732,0.00009933324,0.00001579542,0.00007109636,0.00008405961,0.0000564972],"domain_scores_gemma":[0.998844,0.0006428594,0.00009499346,0.00009066614,0.0002308842,0.0000965332],"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":[0.0001687964,0.00008533441,0.000498764,0.000050942,0.00002839722,0.00003521683,0.00003263105,0.9523848,0.002193384,0.007577267,0.0009220648,0.03602246],"study_design_scores_gemma":[0.000007201056,0.00001648841,0.00003666237,0.000001651512,0.00000185513,0.000002152135,0.000001091139,0.9970546,0.000251587,0.002551034,0.00007380198,0.000001880635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03225144,0.0001921787,0.9652154,0.0001653611,0.00006636364,0.00003940418,0.00006696967,0.0006190053,0.001383801],"genre_scores_gemma":[0.9510553,0.00007343607,0.04707665,0.00007291519,0.00001984436,0.00008393288,0.0000898396,0.00005790521,0.001470265],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006798736,"threshold_uncertainty_score":0.01351833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02894462978211232,"score_gpt":0.3041871407674779,"score_spread":0.2752425109853656,"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."}}