{"id":"W2114500662","doi":"10.1142/s0129183101002851","title":"DEEP-SARSA: A REINFORCEMENT LEARNING ALGORITHM FOR AUTONOMOUS NAVIGATION","year":2001,"lang":"en","type":"article","venue":"International Journal of Modern Physics C","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Reinforcement learning; Computer science; Convergence (economics); Algorithm; Artificial intelligence; Q-learning; Learning classifier system; Robot; Graph; Theoretical computer science","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":[0.000360286,0.0001427641,0.0001778686,0.0001148264,0.00009506625,0.0002485373,0.001106094,0.00004752737,0.000006892701],"category_scores_gemma":[0.00005999599,0.0001406223,0.0001895801,0.0001147263,0.0000252471,0.0009921149,0.0001573311,0.0002826525,0.00001363183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002368326,"about_ca_system_score_gemma":0.0001170734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003628931,"about_ca_topic_score_gemma":1.629289e-7,"domain_scores_codex":[0.9982226,0.00003356324,0.000548294,0.0001666915,0.0008120139,0.0002167817],"domain_scores_gemma":[0.9978821,0.0001260372,0.0007640019,0.0001650441,0.0009855969,0.00007726871],"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":[0.00001214098,0.00002560608,0.00009628655,0.000002224588,0.00009820267,0.00002030011,0.0004353164,0.6839582,0.0002535062,0.004254994,0.0000527715,0.3107905],"study_design_scores_gemma":[0.0008868439,0.000222991,0.00005276545,0.00005813767,0.00001432385,0.00013579,0.0000162473,0.9802066,0.0007314762,0.01284393,0.004693277,0.0001376298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00104024,0.00005024949,0.9965208,0.0004531159,0.001097618,0.000115223,5.052745e-7,0.00004153732,0.0006807032],"genre_scores_gemma":[0.798951,0.00005259624,0.1989756,0.0002279967,0.0009643347,0.000007886013,0.00002225184,0.00002052434,0.0007778116],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7979107,"threshold_uncertainty_score":0.5734411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01994058600414072,"score_gpt":0.2823315718161346,"score_spread":0.2623909858119939,"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."}}