{"id":"W2585136924","doi":"10.1299/jsmekansai.2004.79._11-19_","title":"1110 Reinforcement Learning in Consideration of Symmetry","year":2004,"lang":"en","type":"article","venue":"The Proceedings of Conference of Kansai Branch","topic":"Game Theory and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Homogeneous space; Symmetry (geometry); Formalism (music); Markov decision process; Reinforcement; Computer science; Theoretical physics; Markov process; Mathematics; Pure mathematics; Artificial intelligence; Physics; Geometry; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00194423,0.0003855915,0.0007756925,0.0003098734,0.0005908301,0.001086859,0.0007547174,0.0008090783,0.003425892],"category_scores_gemma":[0.00567578,0.0001878632,0.001011836,0.0003148675,0.002300289,0.002797945,0.001468494,0.001758124,0.0002892221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001470211,"about_ca_system_score_gemma":0.001589964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001302193,"about_ca_topic_score_gemma":0.0006822405,"domain_scores_codex":[0.9983076,0.0008791244,0.00008301507,0.0002360413,0.0003612488,0.0001329204],"domain_scores_gemma":[0.99747,0.00144231,0.000331825,0.000312161,0.0002852662,0.0001584419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003871437,0.00002483027,0.0005389987,0.00005522366,0.0000250181,0.0001002117,0.0001121824,0.04524018,0.0009787639,0.9409339,0.0006729685,0.0112791],"study_design_scores_gemma":[0.00002896432,0.00007345441,0.0001775328,0.00001860304,0.00001229115,0.00006054677,0.00003285983,0.2811206,0.0005897775,0.714905,0.002966962,0.0000134636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03422103,0.0004408816,0.9390875,0.00193656,0.0001758607,0.0000564023,0.00004869459,0.00007976827,0.02395335],"genre_scores_gemma":[0.9007265,0.000460177,0.09164017,0.0003433748,0.0002024542,0.0001270041,0.00006136845,0.00004206986,0.006396939],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003425892,"threshold_uncertainty_score":0.01146078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.079890098860958,"score_gpt":0.3343092779901253,"score_spread":0.2544191791291673,"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."}}