{"id":"W2997475283","doi":"10.1609/aaai.v34i04.5857","title":"Algorithmic Improvements for Deep Reinforcement Learning Applied to Interactive Fiction","year":2020,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; McGill University","funders":"Compute Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Observability; Computer science; Artificial intelligence; Action (physics); Function (biology); Domain (mathematical analysis); Baseline (sea); Point (geometry); Machine learning; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002452252,0.001140201,0.0009240765,0.00051834,0.0005916187,0.001023654,0.002071881,0.001448726,0.005944788],"category_scores_gemma":[0.009233575,0.0005076255,0.0005949201,0.0003813143,0.001297021,0.001502092,0.002316016,0.002824365,0.0007875579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001823423,"about_ca_system_score_gemma":0.002349008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005507503,"about_ca_topic_score_gemma":0.007284951,"domain_scores_codex":[0.9989412,0.0003724019,0.00006071794,0.0002195616,0.0002835359,0.0001225734],"domain_scores_gemma":[0.9972433,0.001774175,0.0001832819,0.0003080026,0.0003408124,0.0001503756],"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":[0.0001324891,0.0002287875,0.001041972,0.0001210413,0.00004186956,0.00006149604,0.000102973,0.8239015,0.002244967,0.04261667,0.001855392,0.1276509],"study_design_scores_gemma":[0.00001941583,0.0000378685,0.00004739507,0.000006497817,0.000004094543,0.000007624792,0.000005000852,0.990431,0.0003132311,0.00859781,0.0005269374,0.000003027823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01535556,0.0002240188,0.9782667,0.0004198447,0.00007030683,0.000126938,0.00003543175,0.0007674661,0.00473374],"genre_scores_gemma":[0.5950165,0.000233103,0.3993095,0.0002777916,0.00009195268,0.0004127503,0.0001336255,0.0001634437,0.004361297],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005944788,"threshold_uncertainty_score":0.01988733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02986483739447762,"score_gpt":0.290029295663619,"score_spread":0.2601644582691414,"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."}}