{"id":"W4416251343","doi":"10.1109/ijcnn64981.2025.11227725","title":"Navigation With QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Reinforcement learning; Trajectory; Planner; Image stitching; Motion planning; Path (computing); State space; Range (aeronautics); Function (biology)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002499764,0.0001136536,0.0001262361,0.0001113269,0.0002080227,0.0001941124,0.0004248258,0.00005495539,0.000005143605],"category_scores_gemma":[0.00007145984,0.00008939203,0.00004068943,0.0003384083,0.0000295636,0.0002784703,0.0001375981,0.0002212037,0.00001408364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003524348,"about_ca_system_score_gemma":0.00007383484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001394763,"about_ca_topic_score_gemma":0.000001685507,"domain_scores_codex":[0.9990146,0.00003431125,0.000192724,0.0002971921,0.000184725,0.0002765139],"domain_scores_gemma":[0.9992471,0.0002848458,0.00006646204,0.0002713582,0.00008502039,0.00004526162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002140096,0.00000958184,0.003245202,0.00003911014,0.00002959049,0.000002718622,0.0002174187,0.4448135,0.000520051,0.5441787,0.0004318057,0.006490889],"study_design_scores_gemma":[0.0005030247,0.0002285551,0.001336462,0.00009495637,0.000009102569,0.000007716872,0.00004930256,0.9823856,0.0009552427,0.00164937,0.01262064,0.0001599861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007083448,0.00001009009,0.9806488,0.001294498,0.0001355914,0.0002413414,1.781068e-7,0.0003087634,0.01027733],"genre_scores_gemma":[0.8127837,0.000001846055,0.181585,0.000509922,0.00003830124,0.00003203453,0.00001380162,0.00001039464,0.005025036],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8057002,"threshold_uncertainty_score":0.3645301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01112330068257593,"score_gpt":0.2746747569265827,"score_spread":0.2635514562440068,"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."}}