{"id":"W3166576966","doi":"10.71781/10508","title":"Deep reinforcement learning for multi-modal embodied navigation","year":2020,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Human Motion and Animation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Canadian Institute for Advanced Research","keywords":"Embodied cognition; Modal; Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; Social psychology; Materials science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006074787,0.0007702792,0.0007537571,0.0002277736,0.0002820236,0.0007196489,0.001019173,0.0009903508,0.00346507],"category_scores_gemma":[0.001741285,0.0004136596,0.0006014738,0.0002766934,0.0006530844,0.001036717,0.001264772,0.00153157,0.0005298909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001077272,"about_ca_system_score_gemma":0.0009732994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01118647,"about_ca_topic_score_gemma":0.01141542,"domain_scores_codex":[0.999754,0.0000623368,0.00001128693,0.00007380614,0.00004894309,0.00004949707],"domain_scores_gemma":[0.9995819,0.000209937,0.00004347738,0.00004733276,0.00008094026,0.00003640659],"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":[0.0001200721,0.00005355337,0.0006708912,0.00009350408,0.00005331056,0.00007651679,0.00009025852,0.9064387,0.004691063,0.01258864,0.001638813,0.0734847],"study_design_scores_gemma":[0.000004918768,0.00001366787,0.00006928705,0.000004902831,0.000003816137,0.000005650604,0.000004410426,0.9956511,0.0004030604,0.003461884,0.0003742184,0.000003170367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02408403,0.0005419102,0.9702954,0.000263743,0.0000863886,0.00002346977,0.00009179975,0.001052977,0.003560246],"genre_scores_gemma":[0.8744217,0.0004148455,0.1146039,0.0001921288,0.00004915597,0.0001176681,0.0002516338,0.0001525465,0.009796363],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01118647,"threshold_uncertainty_score":0.02224272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04756118423734568,"score_gpt":0.3198444224510852,"score_spread":0.2722832382137396,"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."}}