{"id":"W4405568984","doi":"10.1007/978-3-031-77688-5_42","title":"Leveraging Single and Multi-task Reinforcement Learning Algorithms for Autonomous Mobile Aloha Robot","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Aloha; Reinforcement learning; Computer science; Task (project management); Mobile robot; Artificial intelligence; Robot; Human–computer interaction; Throughput; Wireless; Engineering; Telecommunications","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":[0.0004617368,0.0004696585,0.0005463231,0.0002292786,0.000384989,0.0004681951,0.0008566191,0.0006189225,0.001498879],"category_scores_gemma":[0.0009189173,0.0002512225,0.0003109913,0.0002138256,0.0004491878,0.000593818,0.0009286746,0.0007380774,0.0003952395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000325582,"about_ca_system_score_gemma":0.0005400141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002920214,"about_ca_topic_score_gemma":0.002796272,"domain_scores_codex":[0.9998419,0.00003144635,0.000009059651,0.00003955961,0.00004223265,0.00003584334],"domain_scores_gemma":[0.9997008,0.0001350162,0.00002956544,0.00003911846,0.00006972782,0.0000258083],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001343727,0.00008156986,0.0005061656,0.00006751443,0.00004589018,0.00008209131,0.00006091782,0.8164381,0.01102398,0.00550359,0.001196498,0.1648593],"study_design_scores_gemma":[0.000004376384,0.0000384368,0.00006972761,0.000002162044,0.000004068919,0.00001338302,0.000003942897,0.997186,0.0006542521,0.001736414,0.0002840927,0.000003230077],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0505862,0.0005686925,0.9430072,0.0001537806,0.0001096435,0.00003748033,0.00001546615,0.000793288,0.004728262],"genre_scores_gemma":[0.9174917,0.0001448645,0.07837908,0.00006043568,0.00003714574,0.00005545477,0.00002709235,0.00004544538,0.003758697],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002920214,"threshold_uncertainty_score":0.005806446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02962780433733567,"score_gpt":0.250649203937621,"score_spread":0.2210213996002854,"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."}}