{"id":"W3211741236","doi":"","title":"Learning in two-player zero-sum partially observable Markov games with perfect recall","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Observable; Zero (linguistics); Computer science; Markov chain; Recall; Zero-sum game; Markov process; Mathematics; Mathematical economics; Game theory; Statistics; Machine learning; Cognitive psychology; Psychology; Physics","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006205395,0.0002305182,0.0002913811,0.0001759034,0.0002635177,0.001839757,0.0004605876,0.00007566524,0.000007220187],"category_scores_gemma":[0.0001721345,0.0001989258,0.00004178643,0.0008888634,0.00003320075,0.005905949,0.0001497234,0.0004667123,0.00006866969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001216972,"about_ca_system_score_gemma":0.0003370045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006695371,"about_ca_topic_score_gemma":0.00001475801,"domain_scores_codex":[0.9976702,0.0002005468,0.0007430154,0.0002731318,0.0006421358,0.0004710192],"domain_scores_gemma":[0.9985614,0.00009225582,0.0004784477,0.0003576684,0.0004143611,0.00009582588],"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":[0.00001302636,0.00000962177,0.01228115,0.0003259373,0.000008075778,0.00001959011,0.002116827,0.9708441,0.0001575819,0.0004777647,0.0002113606,0.01353496],"study_design_scores_gemma":[0.0006628475,0.0001150273,0.001499762,0.0004046723,0.000006000048,0.0001319234,0.0004208151,0.9867987,0.0004495157,0.000006762432,0.009234232,0.0002697153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06168626,0.0002322497,0.9256225,0.0005857725,0.0006888983,0.0003958468,5.808805e-7,0.000581209,0.01020674],"genre_scores_gemma":[0.988368,0.000009526449,0.00906817,0.0003815529,0.00005129398,0.00004609138,0.00002781352,0.00001507453,0.002032431],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9266818,"threshold_uncertainty_score":0.9991964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0187638513781867,"score_gpt":0.2540259796019725,"score_spread":0.2352621282237858,"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."}}