{"id":"W3031516940","doi":"10.48550/arxiv.2003.10249","title":"Using Deep Reinforcement Learning Methods for Autonomous Vessels in 2D Environments","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Maritime Navigation and Safety","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Context (archaeology); Motion planning; Agile software development; Planner; Bellman equation; Function (biology); Machine learning; Robot; Mathematical optimization; Mathematics","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":[0.0002537874,0.000259833,0.000332719,0.000155542,0.00007421227,0.00002875283,0.0002800967,0.0002646795,0.0001252099],"category_scores_gemma":[0.00003706534,0.000365511,0.0001461427,0.0001851117,0.00002472773,0.0001066074,0.0003058208,0.0006213517,0.00001959867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005831682,"about_ca_system_score_gemma":0.00004069809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003798305,"about_ca_topic_score_gemma":0.000004490836,"domain_scores_codex":[0.9988458,0.0001029922,0.0002636192,0.0004625528,0.00004378621,0.0002812262],"domain_scores_gemma":[0.9994045,0.00009699069,0.00009750057,0.0002639416,0.00001457669,0.0001224114],"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":[0.00002114186,0.00001015597,0.0003201328,0.0001670513,0.00006681701,0.00002107739,0.0002341648,0.9936544,0.0009498452,0.002673827,0.000006803628,0.001874568],"study_design_scores_gemma":[0.0005578731,0.00001816532,0.000205596,0.00005896998,0.00006598856,6.622385e-7,0.00009112663,0.9904292,0.0007922806,0.002500029,0.004938717,0.000341415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02638094,0.00006163419,0.9692254,0.00001326796,0.0002564478,0.000459664,0.0000033323,0.0001579119,0.003441403],"genre_scores_gemma":[0.9817127,0.0001308453,0.01747243,0.00003323717,0.00004605427,0.000003271238,0.00007361206,0.00004542609,0.0004824036],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9553318,"threshold_uncertainty_score":0.9998797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09631121055334327,"score_gpt":0.2432798862094639,"score_spread":0.1469686756561207,"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."}}