{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000627008,0.0004584626,0.0004776779,0.0007137726,0.0005411441,0.000301626,0.002525657,0.0003853787,0.00008552512],"category_scores_gemma":[0.0001962997,0.0005723861,0.0004203317,0.0008586952,0.0001331497,0.000453762,0.002950499,0.00106048,0.0002080305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004056279,"about_ca_system_score_gemma":0.0004675473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005223161,"about_ca_topic_score_gemma":0.000001615526,"domain_scores_codex":[0.9971841,0.0001595197,0.0004063893,0.001312898,0.0002424116,0.0006946911],"domain_scores_gemma":[0.9967995,0.0007948693,0.0003697372,0.001397038,0.0004414864,0.000197325],"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":[0.00002696279,0.00002954145,0.0005226924,0.0001813434,0.0001339916,0.00003191434,0.0002055664,0.9204964,0.0000749016,0.07749747,0.0006529156,0.0001463034],"study_design_scores_gemma":[0.0008508962,0.000226209,0.0001899934,0.0001961628,0.00009412595,0.000001589007,0.0000463535,0.9927149,0.0007355988,0.002878198,0.001508515,0.0005574771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003186018,0.00001302054,0.9854887,0.0001923541,0.0004768641,0.000989108,0.00001536333,0.0005771092,0.009061481],"genre_scores_gemma":[0.9076249,0.0001055197,0.005383275,0.0001843097,0.00008045218,0.000009797863,0.0001750533,0.00002564224,0.08641105],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9801054,"threshold_uncertainty_score":0.9996728,"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."}}