{"id":"W3014436489","doi":"10.48550/arxiv.2004.01097","title":"Learning to cooperate: Emergent communication in multi-agent navigation","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Task (project management); Property (philosophy); Protocol (science); Space (punctuation); Core (optical fiber); Artificial intelligence; State (computer science); Human–computer interaction; State space; Communications protocol; Distributed computing; Telecommunications; Engineering; Computer network; Mathematics","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":[0.0008306163,0.0001848573,0.0002652543,0.0003213483,0.0006848315,0.001031884,0.0004962662,0.0007092942,0.0009546607],"category_scores_gemma":[0.007706017,0.0001691665,0.0002963482,0.0002874153,0.002288245,0.001760862,0.001270853,0.000863798,0.0001053038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006348593,"about_ca_system_score_gemma":0.0005646535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001517804,"about_ca_topic_score_gemma":0.001114725,"domain_scores_codex":[0.9994584,0.0003182387,0.00002090392,0.00008277175,0.00007598613,0.00004378882],"domain_scores_gemma":[0.9966987,0.002185588,0.0003979789,0.0003050741,0.0002366203,0.000176068],"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":[0.00008059188,0.00009324388,0.008214149,0.0001094102,0.00007063014,0.0004624424,0.003103984,0.2263629,0.01382328,0.7166023,0.001454144,0.02962294],"study_design_scores_gemma":[0.0000238582,0.00004014977,0.001592734,0.0000123236,0.00001333996,0.00008276533,0.0004770023,0.5176677,0.001545914,0.4769521,0.001571708,0.00002039439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4641958,0.0001712713,0.5243245,0.001474871,0.00003907537,0.00003682289,0.00005553434,0.0001752201,0.009526969],"genre_scores_gemma":[0.9702451,0.0000743877,0.0286474,0.00007408081,0.00001569258,0.00004224082,0.00002857696,0.00002295884,0.0008495566],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001517804,"threshold_uncertainty_score":0.004606307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1333156524103679,"score_gpt":0.262040545679653,"score_spread":0.1287248932692851,"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."}}