{"id":"W2767806554","doi":"10.1109/tg.2018.2861759","title":"Exploration in NetHack With Secret Discovery","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Games","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Heuristics; Automation; Point (geometry); Greedy algorithm; Feature (linguistics); Face (sociological concept); Identification (biology)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001293353,0.0001366711,0.0001211482,0.0001949747,0.0001054979,0.0001887434,0.0003855324,0.00005770112,0.00004043482],"category_scores_gemma":[0.000004371642,0.0001148328,0.00003933604,0.0005631902,0.0001682178,0.001961719,0.000002069979,0.0001686461,0.0002330865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005524292,"about_ca_system_score_gemma":0.00006475965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001285009,"about_ca_topic_score_gemma":0.001549321,"domain_scores_codex":[0.9989035,0.00006027577,0.000203912,0.0003582712,0.0002370359,0.0002370638],"domain_scores_gemma":[0.9992819,0.00009246394,0.00004867341,0.0004566393,0.00006882566,0.00005146531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005068174,0.001236112,0.0008994898,0.00004086005,0.00008940574,0.00009239192,0.03556713,0.1243341,0.01010124,0.01935787,0.001251065,0.8065235],"study_design_scores_gemma":[0.0003820048,0.001589007,0.0008259862,0.0001590643,0.00001621472,0.00002624271,0.00133262,0.1510778,0.829636,0.0113182,0.002945728,0.000691183],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07797594,0.00001006724,0.9194468,0.0008087681,0.0005064096,0.0001489289,0.000002455475,0.0001379091,0.000962686],"genre_scores_gemma":[0.989819,0.0000172054,0.008949008,0.0002736001,0.00006853154,0.00004765614,4.364938e-7,0.00001192351,0.0008125756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9118431,"threshold_uncertainty_score":0.4682744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0362188523720771,"score_gpt":0.2777737804913865,"score_spread":0.2415549281193093,"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."}}