{"id":"W4408146705","doi":"10.1109/icmla61862.2024.00012","title":"Leveraging A* Pathfinding for Efficient Deep Reinforcement Learning in Obstacle-Dense Environments","year":2024,"lang":"en","type":"article","venue":"","topic":"VLSI and FPGA Design Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thales (Canada)","funders":"","keywords":"Pathfinding; Reinforcement learning; Computer science; Obstacle; Artificial intelligence; Human–computer interaction; Theoretical computer science; Graph; Geography","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":[0.0002295239,0.0001338747,0.0001123578,0.0001799964,0.00004398318,0.00006334428,0.0000711808,0.00005752046,0.0000709376],"category_scores_gemma":[0.00001252376,0.0001321707,0.00005495329,0.0001120369,0.0000082133,0.00006768535,0.00002579423,0.0001684114,0.00003977118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002229951,"about_ca_system_score_gemma":0.000005323998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005612058,"about_ca_topic_score_gemma":0.000001164452,"domain_scores_codex":[0.9991886,0.000009499695,0.0002141558,0.0001767413,0.0001175739,0.000293434],"domain_scores_gemma":[0.999781,0.00007239926,0.000008860526,0.00009530615,0.000002615252,0.00003985146],"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":[0.000003275612,0.000008320811,0.0001619834,0.0001326962,0.00002091015,0.00002482123,0.001451147,0.9346055,0.02478582,0.0007305561,0.0002050298,0.03786992],"study_design_scores_gemma":[0.000145668,0.00003208711,0.0000950169,0.0001023657,0.000007040052,0.000003869485,0.0001884942,0.9638231,0.02817447,0.000102871,0.007145578,0.000179482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07304282,0.0005859332,0.9216596,0.00001567901,0.0001907514,0.0003232431,3.652628e-7,0.0008666994,0.003314851],"genre_scores_gemma":[0.9963871,0.00006033825,0.002429268,0.00002044079,0.0000349248,0.0001007212,0.000007967543,0.0000442935,0.0009149299],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9233443,"threshold_uncertainty_score":0.5389765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01343362425897058,"score_gpt":0.2192768892541057,"score_spread":0.2058432649951351,"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."}}