{"id":"W2756674674","doi":"10.1609/aiide.v13i1.12923","title":"Learning Combat in NetHack","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Scripting language; Computer science; Automation; Adversary; Variety (cybernetics); Point (geometry); Action (physics); Artificial intelligence; Human–computer interaction; Space (punctuation); Software engineering; Machine learning; Programming language; Computer security; Engineering","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":[0.0007109268,0.001293884,0.0005686604,0.0004792164,0.0004249986,0.001085335,0.0009576443,0.0009111363,0.003039112],"category_scores_gemma":[0.002333347,0.0003205274,0.0004552131,0.000189816,0.0005088062,0.001182976,0.0007694726,0.001247802,0.0007094541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007963094,"about_ca_system_score_gemma":0.0006025901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005989603,"about_ca_topic_score_gemma":0.008812133,"domain_scores_codex":[0.9996201,0.0001253701,0.00001665299,0.0001325863,0.00005385555,0.0000513568],"domain_scores_gemma":[0.999252,0.0004617701,0.00004821207,0.00004894959,0.0001026438,0.00008631259],"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":[0.0008397556,0.0008613521,0.0211001,0.0001818796,0.0001323061,0.0002562858,0.0002525822,0.6514866,0.00541313,0.008066441,0.007080875,0.3043288],"study_design_scores_gemma":[0.00002147505,0.0001107518,0.001184733,0.00001182531,0.000006399081,0.00002164847,0.00006650898,0.9924964,0.001211742,0.003767172,0.001094704,0.00000679939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7184002,0.0006996084,0.261775,0.000900988,0.0001706883,0.0003946996,0.0004854696,0.002644609,0.0145287],"genre_scores_gemma":[0.9291323,0.0001542394,0.06042344,0.0002338772,0.00003897744,0.0001361017,0.001095537,0.00007389399,0.008711645],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005989603,"threshold_uncertainty_score":0.01190948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04371482850026954,"score_gpt":0.2891511786187464,"score_spread":0.2454363501184769,"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."}}