{"id":"W2991419354","doi":"10.1109/itsc.2019.8916928","title":"Multi-lane Cruising Using Hierarchical Planning and Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Reinforcement learning; Abstraction; Computer science; Modular design; Hierarchy; Motion (physics); Motion planning; Artificial intelligence; State space; Action (physics); Set (abstract data type); Human–computer interaction; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003649163,0.0001782826,0.0001985558,0.000159057,0.0002101736,0.0003642311,0.0003934719,0.00007459876,0.00006371711],"category_scores_gemma":[0.00007128086,0.0001646126,0.0000389064,0.0002036213,0.00003996005,0.0005855584,0.0005668644,0.000452734,0.00008441533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005842707,"about_ca_system_score_gemma":0.00004773557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002622024,"about_ca_topic_score_gemma":2.346424e-7,"domain_scores_codex":[0.9984441,0.00006714398,0.0003034006,0.0003999095,0.0003576489,0.0004277513],"domain_scores_gemma":[0.9992129,0.0001415172,0.0001215669,0.0003563619,0.00004290978,0.0001247014],"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":[0.000003849759,0.000004803479,0.02063072,0.00002096261,0.00001412789,0.000009441941,0.0006629816,0.9706799,0.003491971,0.003378644,0.00001058298,0.001091953],"study_design_scores_gemma":[0.0005217836,0.0001199683,0.002523199,0.00007648132,0.000004587467,0.00003295367,0.0000823592,0.9948334,0.0003191649,0.00002689422,0.001230235,0.000228946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06295869,0.00006409093,0.9312754,0.00009807212,0.0002337507,0.0001811628,2.48417e-8,0.0002281729,0.004960589],"genre_scores_gemma":[0.7072219,0.000004707838,0.2891697,0.0001989716,0.0000303888,0.000001214931,0.000001804203,0.0000128423,0.003358423],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6442633,"threshold_uncertainty_score":0.6712707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03906097747933342,"score_gpt":0.2925437606726954,"score_spread":0.253482783193362,"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."}}