{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000086696,0.0001676373,0.0001869847,0.00005036331,0.0001105422,0.0001857039,0.0001681919,0.0001453666,0.001097754],"category_scores_gemma":[0.00003038942,0.0001936041,0.00006421498,0.00005684753,0.000003649458,0.0001734893,0.00001328063,0.0002050956,0.0005339548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000070599,"about_ca_system_score_gemma":0.00002274211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003368923,"about_ca_topic_score_gemma":0.00005404189,"domain_scores_codex":[0.9992724,0.00001169605,0.0002752682,0.0001929282,0.0001135028,0.0001341819],"domain_scores_gemma":[0.9997042,0.0000117308,0.00009243918,0.00007675201,0.00005757538,0.00005734684],"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":[0.0001893389,0.00005114297,0.00002027195,0.001118778,0.0002526257,0.000006809371,0.02709006,0.6396187,0.03101135,0.0005898946,0.001063208,0.2989878],"study_design_scores_gemma":[0.0007398825,0.00005919952,0.0001353407,0.0001797999,0.00004559119,3.978416e-7,0.001214201,0.9508741,0.009775619,0.00001583044,0.03667452,0.0002854485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1086483,0.0002697617,0.5183067,0.00007840974,0.002777625,0.006658028,0.00001937833,0.0001241865,0.3631175],"genre_scores_gemma":[0.9435269,0.00002049046,0.01567671,0.00001397347,0.0001969762,0.0002087051,0.01762421,0.00009186367,0.02264024],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8348785,"threshold_uncertainty_score":0.9998154,"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."}}