{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003394195,0.0001925686,0.0001868134,0.0001608574,0.0003313131,0.0003922057,0.0002695439,0.00005838629,0.000001802124],"category_scores_gemma":[0.00007239057,0.0001800103,0.00006170283,0.0003493013,0.00004785861,0.0003870616,0.0000447926,0.0001078075,0.00003099171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006704871,"about_ca_system_score_gemma":0.00005292968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005202972,"about_ca_topic_score_gemma":0.000002596449,"domain_scores_codex":[0.9985096,0.00005176422,0.0003155372,0.0003657854,0.0003422957,0.0004149831],"domain_scores_gemma":[0.9990896,0.0002389,0.000179199,0.0003045986,0.00009178499,0.00009591697],"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":[0.000004269971,0.0000187175,0.001666277,0.000130748,0.00002229512,0.00001108271,0.0001399118,0.9902044,0.005443348,0.0008630463,0.0009151591,0.0005807313],"study_design_scores_gemma":[0.0008383132,0.0001107829,0.009727848,0.0001167885,0.00002932468,0.000002630575,0.00001621026,0.98825,0.0003812626,0.00002354516,0.0002674729,0.0002358563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03173956,0.000006417311,0.9619867,0.004795012,0.0005736906,0.0004034056,0.00000383556,0.0004876241,0.000003739416],"genre_scores_gemma":[0.7800946,0.000005541786,0.2182176,0.00127649,0.00007913647,0.00005726359,0.00005742662,0.0000308208,0.000181063],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7483551,"threshold_uncertainty_score":0.7340608,"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."}}