{"id":"W3041349757","doi":"10.24963/ijcai.2020/764","title":"RLCard: A Platform for Reinforcement Learning in Card Games","year":2020,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Reinforcement learning; Debugging; Python (programming language); Human–computer interaction; Visualization; Bridging (networking); Multimedia; Artificial intelligence; Programming language","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":[0.0001788207,0.0000987755,0.0001451344,0.00005365144,0.0000532818,0.00009862342,0.0005089461,0.00003920137,0.00003140114],"category_scores_gemma":[0.0002106097,0.00008571577,0.0000686908,0.0002459169,0.00002166768,0.0003803308,0.0001930058,0.000117162,0.0001062073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004042561,"about_ca_system_score_gemma":0.00005278555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006776312,"about_ca_topic_score_gemma":0.00003076098,"domain_scores_codex":[0.9990118,0.00001067173,0.0002586585,0.0002772115,0.0001736504,0.0002680338],"domain_scores_gemma":[0.9995238,0.0001294039,0.00004729644,0.0001680232,0.00004550624,0.00008602599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005445668,0.00002778725,0.003995404,0.00005588231,0.00003034895,0.00001960612,0.02090991,0.2697309,0.001614839,0.3296416,0.00578025,0.3681391],"study_design_scores_gemma":[0.0001017672,0.0002204363,0.00008456977,0.0000113627,0.000001569016,0.000001013319,0.0007047791,0.9255062,0.02289592,0.00258338,0.04772857,0.00016039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007163235,0.00003295902,0.9777486,0.00364872,0.0001210464,0.0002792555,1.752608e-7,0.0002150006,0.01079097],"genre_scores_gemma":[0.9745503,0.000009269821,0.02304718,0.001492015,0.00007057573,0.00004347811,0.000001139674,0.000006812777,0.0007792356],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9673871,"threshold_uncertainty_score":0.3495388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06500251615242786,"score_gpt":0.2965336277008747,"score_spread":0.2315311115484468,"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."}}