{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002906739,0.0005194893,0.0003342222,0.0002142934,0.0002224965,0.0004271718,0.0008752387,0.0004306392,0.00110563],"category_scores_gemma":[0.0008188865,0.0002282889,0.0002016173,0.0001875642,0.0003823006,0.0006722814,0.0008574426,0.0007374127,0.0003493012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002853068,"about_ca_system_score_gemma":0.0007556317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002530613,"about_ca_topic_score_gemma":0.003132015,"domain_scores_codex":[0.9998784,0.00001984073,0.000006770455,0.00003192492,0.00003931902,0.00002371103],"domain_scores_gemma":[0.9996905,0.0001078394,0.00004393843,0.00005338387,0.00007065789,0.00003358963],"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":[0.0001248207,0.0001773583,0.001801368,0.00007997549,0.00005815551,0.0001323719,0.00008476874,0.6695894,0.04485178,0.009589151,0.001758959,0.2717518],"study_design_scores_gemma":[0.000007711924,0.00005506118,0.0001161574,0.000003216213,0.000004494213,0.00002195637,0.000005755197,0.9934616,0.003291775,0.002286862,0.0007412229,0.000004283152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03345151,0.0001003499,0.9635224,0.00009120339,0.00003188408,0.00002311472,0.00001763902,0.0009041747,0.001857669],"genre_scores_gemma":[0.7437711,0.0001128316,0.2537432,0.0001048835,0.00001759052,0.00005740209,0.00006420579,0.00007222522,0.002056586],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002530613,"threshold_uncertainty_score":0.005031824,"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."}}