{"id":"W3172545192","doi":"10.1007/978-3-031-26889-2_19","title":"Least-Restrictive Multi-agent Collision Avoidance via Deep Meta Reinforcement Learning and Optimal Control","year":2023,"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":"University of Regina; Simon Fraser University","funders":"","keywords":"Reinforcement learning; Collision avoidance; Computer science; Collision; Function (biology); Interrupt; Trajectory; Artificial intelligence; Autonomous agent; Control (management); Control theory (sociology); Computer security","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":[0.0008418073,0.0006938701,0.00114702,0.0002997139,0.0003250814,0.0004915037,0.0004857269,0.0006672094,0.000006947585],"category_scores_gemma":[0.0001372381,0.0005854881,0.0001723826,0.0001900576,0.0001148992,0.0001897777,0.0004590493,0.001432049,0.00001391126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001621543,"about_ca_system_score_gemma":0.00004473385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009486178,"about_ca_topic_score_gemma":0.00003770982,"domain_scores_codex":[0.9967689,0.000186092,0.0008620158,0.0009564947,0.0006054567,0.0006210575],"domain_scores_gemma":[0.9973953,0.001090065,0.0006824888,0.0005017766,0.0001471089,0.0001832981],"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":[0.00002228546,0.000004240243,0.000130552,0.0001106866,0.0004086246,0.00007132311,0.0003051482,0.992794,0.000004123491,0.003090578,0.00002441893,0.003033972],"study_design_scores_gemma":[0.0008864863,0.0002793884,0.00004244147,0.0004005769,0.0002258939,0.00003421505,0.000007180019,0.9941675,0.00000200547,0.00009852597,0.003300589,0.0005551848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000008331048,0.01193503,0.983928,0.00007602413,0.00113463,0.001164099,0.000001725386,0.0001774677,0.001574711],"genre_scores_gemma":[0.9644711,0.003306362,0.004574791,0.0001823767,0.000559754,0.0001374971,0.00004230524,0.0001409461,0.02658487],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9793532,"threshold_uncertainty_score":0.9996597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02381156961467746,"score_gpt":0.2422548505839882,"score_spread":0.2184432809693107,"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."}}