{"id":"W4383112356","doi":"10.1109/lra.2023.3292004","title":"SACHA: Soft Actor-Critic With Heuristic-Based Attention for Partially Observable Multi-Agent Path Finding","year":2023,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Heuristic; Path (computing); Observable; Computer science; Mathematical optimization; Artificial intelligence; Mathematics; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001332157,0.00146157,0.001172767,0.0004499835,0.0004544242,0.000850018,0.002087008,0.001554043,0.002704598],"category_scores_gemma":[0.003767021,0.0006376496,0.0006315458,0.0003649112,0.001220824,0.0008705578,0.001513963,0.002190691,0.0006008203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009468262,"about_ca_system_score_gemma":0.002154087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007154312,"about_ca_topic_score_gemma":0.007945433,"domain_scores_codex":[0.9994237,0.0001731252,0.00002854832,0.0001328476,0.0001607864,0.00008093238],"domain_scores_gemma":[0.9984221,0.0009333038,0.0001785136,0.0001094686,0.0002243213,0.0001322625],"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":[0.00005228772,0.00003036803,0.0003003409,0.00004565621,0.00004287974,0.00007389802,0.00003894731,0.9634426,0.001161324,0.007930898,0.001451189,0.02542959],"study_design_scores_gemma":[0.000007489999,0.000008619661,0.00001804402,0.000002204301,0.000002753444,0.000004601144,0.000001438907,0.9981621,0.0001542028,0.001421181,0.0002153371,0.000002057262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006797676,0.000227078,0.989282,0.0002075019,0.00008242018,0.00005950072,0.00002978643,0.0008688942,0.002445142],"genre_scores_gemma":[0.7372437,0.0002905347,0.2542422,0.0004617432,0.0001207975,0.0003857711,0.0001778999,0.0002333073,0.006844076],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007154312,"threshold_uncertainty_score":0.01422536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0428821579873367,"score_gpt":0.2687953178799828,"score_spread":0.2259131598926461,"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."}}