{"id":"W4391494285","doi":"10.1007/s13042-023-02063-6","title":"Expected Lenient Q-learning: a fast variant of the Lenient Q-learning algorithm for cooperative stochastic Markov games","year":2024,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Rimouski","funders":"Centre National pour la Recherche Scientifique et Technique","keywords":"Algorithm; Convergence (economics); Reinforcement learning; Markov chain; Computer science; Q-learning; Rate of convergence; Artificial intelligence; Markov decision process; Mathematics; Markov process; Machine learning; Key (lock)","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":[0.0008565587,0.0002500363,0.0003251078,0.0003044513,0.0001992351,0.0004545461,0.0009206132,0.00008797869,0.00003550599],"category_scores_gemma":[0.0009930161,0.0001813006,0.0002324593,0.0002867837,0.0001280271,0.0002523298,0.0004291756,0.001253746,0.00000383342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001148033,"about_ca_system_score_gemma":0.0001901367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002129648,"about_ca_topic_score_gemma":0.000001770802,"domain_scores_codex":[0.9973768,0.0003293143,0.0007537713,0.0003046692,0.0009614087,0.0002740317],"domain_scores_gemma":[0.9974262,0.0008045321,0.0006740268,0.0001411209,0.0008458442,0.0001083165],"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":[0.00005177798,0.00006199234,0.000847643,0.00003242887,0.0004598645,0.00005314804,0.00507356,0.8793574,0.0005165637,0.004562635,0.0001743822,0.1088086],"study_design_scores_gemma":[0.000815627,0.0008114401,0.000587703,0.0004578394,0.00006953004,0.0004812743,0.00044606,0.9793282,0.0002617548,0.0001541737,0.01639202,0.0001943403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0100133,0.00146644,0.9850867,0.001273839,0.001605347,0.0001739597,0.000005222928,0.00006320367,0.000311937],"genre_scores_gemma":[0.969007,0.0002772888,0.02631722,0.00005901456,0.0003144332,0.00000742542,0.000009309568,0.00003528421,0.003972988],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9589937,"threshold_uncertainty_score":0.7393224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007476805942429175,"score_gpt":0.2578004923334482,"score_spread":0.250323686391019,"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."}}