{"id":"W2171609577","doi":"10.1109/ical.2009.5262570","title":"Neural Q-learning in motion planning for mobile robot","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Algorithms and Applications","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Reinforcement learning; Convergence (economics); Q-learning; Computer science; Property (philosophy); Artificial neural network; Mobile robot; Motion planning; Artificial intelligence; Motion (physics); Robot; Robot learning; Machine learning","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":[0.0000210559,0.00004381496,0.00004740049,0.00002825149,0.00002742408,0.000008185811,0.00002727048,0.00001930701,0.000008122853],"category_scores_gemma":[0.000003401052,0.00004410772,0.00001442821,0.00006953561,0.000002069632,0.00006998504,0.000002069063,0.00006465801,0.000003200147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001498114,"about_ca_system_score_gemma":8.503102e-7,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001212941,"about_ca_topic_score_gemma":9.666174e-7,"domain_scores_codex":[0.9997398,0.000001364246,0.00007184532,0.00006179111,0.00002157625,0.0001035738],"domain_scores_gemma":[0.9999168,0.00001517079,0.000005977376,0.00003938263,0.00000591949,0.00001674319],"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":[4.72839e-7,0.000004493262,0.00006180376,0.00000202656,4.644889e-7,1.892945e-7,0.00004161282,0.8912877,0.002536214,0.0003132565,0.00003334034,0.1057185],"study_design_scores_gemma":[0.0001351765,0.00002594423,0.005357486,0.000004611262,8.901722e-7,8.359518e-7,0.00009084809,0.9900358,0.001026471,0.0006391273,0.002616457,0.00006636461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08555724,0.00007738449,0.9120069,0.00004686163,0.00003282611,0.0001868454,8.040958e-7,0.0003064114,0.001784676],"genre_scores_gemma":[0.9786673,0.000003958404,0.02102288,0.00002359567,0.00004465085,0.00006420364,0.000009641092,0.000007081042,0.0001566501],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8931101,"threshold_uncertainty_score":0.1798661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01066909240656045,"score_gpt":0.2664143892816936,"score_spread":0.2557452968751332,"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."}}