{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006661996,0.000773919,0.001008116,0.0003357119,0.0004013167,0.001034787,0.001580034,0.001194128,0.004736771],"category_scores_gemma":[0.001669233,0.0004481169,0.000520588,0.0007765508,0.001390839,0.00151432,0.001574577,0.002367473,0.0008936547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007773341,"about_ca_system_score_gemma":0.001115604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00365091,"about_ca_topic_score_gemma":0.003754383,"domain_scores_codex":[0.9997196,0.000103192,0.000009482983,0.00005132332,0.00008923892,0.0000271109],"domain_scores_gemma":[0.9995542,0.0002983468,0.0000223411,0.00003891285,0.00005505724,0.00003122886],"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":[0.00005015314,0.0000543923,0.0001192625,0.0001459615,0.00003314971,0.00004406495,0.00007802677,0.7486693,0.001298454,0.1252567,0.003364229,0.1208862],"study_design_scores_gemma":[0.000005706514,0.00002299616,0.00002873374,0.00001317381,0.000005797197,0.00001148486,0.000006723443,0.9335473,0.0002597243,0.06370518,0.002387789,0.000005337365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001929932,0.0008900865,0.9911809,0.0002254075,0.00005566715,0.00001303002,0.00001299469,0.000161034,0.005530843],"genre_scores_gemma":[0.3957497,0.004387053,0.5702757,0.000367832,0.0003363995,0.0001741152,0.0001089095,0.0003003034,0.02829996],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004736771,"threshold_uncertainty_score":0.01584613,"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."}}