{"id":"W2996187564","doi":"","title":"Decentralized Distributed PPO: Mastering PointGoal Navigation","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Reinforcement learning; Speedup; Leverage (statistics); Robot; Task (project management); Artificial intelligence; Distributed computing; Computation; Autonomous agent; Compass; Real-time computing; Parallel computing; Algorithm","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":[0.00006586644,0.0001172316,0.0001127815,0.00003599506,0.0001439697,0.00007378168,0.0007413666,0.0000471447,0.00003588499],"category_scores_gemma":[0.00004001418,0.0001390838,0.00006300002,0.000770312,0.00003515749,0.0003988699,0.0002762724,0.0001709045,0.0002666744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007275185,"about_ca_system_score_gemma":0.00003040714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001028744,"about_ca_topic_score_gemma":0.000002400585,"domain_scores_codex":[0.9990555,0.00007040716,0.000113142,0.0004778898,0.00006072902,0.0002223391],"domain_scores_gemma":[0.99924,0.00005052158,0.00008604687,0.0003615178,0.00005540232,0.0002064519],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007716467,0.0001220187,0.04966931,0.00004859167,0.00006641699,0.0002135317,0.00116152,0.3285196,0.006637393,0.6081917,0.0003860766,0.004906596],"study_design_scores_gemma":[0.000565982,0.00003300617,0.01647596,0.000009541393,0.00001093866,0.00000387569,0.00003020128,0.9785212,0.0003938059,0.002159366,0.001625395,0.0001706976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3819372,0.000004068536,0.6163808,0.001026124,0.00003280666,0.00008741894,0.000005634839,0.0002760137,0.0002499603],"genre_scores_gemma":[0.994449,0.000004980287,0.005229745,0.0002158082,0.0000259203,5.971312e-7,0.00003005953,0.000008009312,0.00003585861],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6500016,"threshold_uncertainty_score":0.5671675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05937336108382171,"score_gpt":0.1911636216772524,"score_spread":0.1317902605934307,"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."}}