{"id":"W4404165606","doi":"10.1007/978-3-031-73151-8_8","title":"Beyond Traditional Motion Planning: A Proximal Policy Optimization Reinforcement Learning Approach for Robotics","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Robotic Path Planning Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Robotics; Motion (physics); Computer science; Robot","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004855757,0.0004313113,0.0005157348,0.0004022662,0.0001751962,0.0004625688,0.000312039,0.0006298769,0.000001087935],"category_scores_gemma":[0.00005461855,0.0003975696,0.0001068555,0.0001612385,0.00004950214,0.000147918,0.0001058071,0.0008018553,9.582725e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002144007,"about_ca_system_score_gemma":0.00009680985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001263658,"about_ca_topic_score_gemma":2.937337e-7,"domain_scores_codex":[0.9978722,0.00004015803,0.0005709984,0.0007278316,0.0003763938,0.0004124173],"domain_scores_gemma":[0.9989531,0.0002905758,0.000294232,0.0002750501,0.00008662537,0.0001004303],"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":[0.000007646754,0.000007300206,0.00000982456,0.000251492,0.00004996589,0.00001448219,0.0002874722,0.8402082,3.101826e-7,0.1574518,0.00006655953,0.001645022],"study_design_scores_gemma":[0.0002729543,0.0001766976,0.000002436335,0.000735503,0.00003445882,0.0001121186,0.000003123462,0.9891195,3.238897e-7,0.008868191,0.0002916814,0.0003829964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[2.61918e-7,0.003613221,0.9777902,0.0001749327,0.0009850559,0.001020911,0.000007142049,0.0001590102,0.01624922],"genre_scores_gemma":[0.1487824,0.0003156371,0.8052902,0.0003717402,0.01143995,0.0004209786,0.002946071,0.0003335407,0.03009943],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1725,"threshold_uncertainty_score":0.9998476,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03333627970345873,"score_gpt":0.2467783373552329,"score_spread":0.2134420576517742,"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."}}