{"id":"W4415318339","doi":"10.48550/arxiv.2510.07257","title":"Test-Time Graph Search for Goal-Conditioned Reinforcement Learning","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Graph; Metric (unit); Bounding overwatch; Base (topology); Train; Learning to rank; Sequence (biology)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001250504,0.001538391,0.001017779,0.0005714698,0.0004403947,0.0008069578,0.002323838,0.001351081,0.005393633],"category_scores_gemma":[0.007016316,0.0005056561,0.0005954562,0.0005305298,0.001204267,0.00153974,0.001682222,0.002478001,0.001252107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001200861,"about_ca_system_score_gemma":0.002249173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006143304,"about_ca_topic_score_gemma":0.009634431,"domain_scores_codex":[0.9993229,0.0002325754,0.0000325189,0.0002114467,0.0001083931,0.00009211707],"domain_scores_gemma":[0.9975979,0.001456734,0.0001435633,0.000430759,0.0002023038,0.0001688512],"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":[0.000307639,0.0002265424,0.002131046,0.0002200649,0.00006557057,0.0001177128,0.00008624499,0.8158912,0.00272208,0.009475751,0.008851841,0.1599043],"study_design_scores_gemma":[0.0000330531,0.00004392104,0.0001099336,0.00001093999,0.000006446257,0.00001251197,0.0000109787,0.9886874,0.0007958654,0.009593284,0.0006907285,0.000004966069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05854515,0.0006710974,0.9235502,0.0006412203,0.0001442084,0.0001837413,0.000558823,0.01024634,0.005459257],"genre_scores_gemma":[0.7454227,0.0001920082,0.2480837,0.0004277494,0.0000476582,0.0003245254,0.001482309,0.0009381853,0.003081306],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006143304,"threshold_uncertainty_score":0.01804346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04836339790260166,"score_gpt":0.2102282857347292,"score_spread":0.1618648878321275,"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."}}