{"id":"W162907590","doi":"10.82308/44454","title":"On characteristics of Markov decision processes and reinforcement learning in large domains","year":2005,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Markov decision process; Artificial intelligence; Machine learning; Task (project management); Instance-based learning; Process (computing); Temporal difference learning; Stability (learning theory); Markov process; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005175161,0.0001952846,0.0002458887,0.0001538605,0.0003751188,0.00006127997,0.000468174,0.00009064758,0.00002078987],"category_scores_gemma":[0.0002953864,0.000183515,0.00004311141,0.000584279,0.00003004957,0.0005893283,0.000332123,0.0004053458,0.00002816868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000983991,"about_ca_system_score_gemma":0.00001685885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009024516,"about_ca_topic_score_gemma":0.00006906698,"domain_scores_codex":[0.9982994,0.00006612346,0.0004791721,0.0004573141,0.0003388719,0.0003591026],"domain_scores_gemma":[0.9987894,0.0003646276,0.0002189434,0.0003894651,0.0001093673,0.0001282329],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004759682,0.0002137655,0.0004911156,0.00006031948,0.00001081889,0.00001154795,0.00001077871,0.001663911,0.003749443,0.3871149,0.000004742821,0.606621],"study_design_scores_gemma":[0.01131706,0.002670286,0.09118392,0.003086974,0.0001027487,0.0001683988,0.0001349535,0.1379622,0.111136,0.1410214,0.4969829,0.004233088],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9944422,0.00005075992,0.0007875934,0.000106684,0.00006560511,0.0002774638,0.00002400305,0.00009155883,0.004154152],"genre_scores_gemma":[0.993494,0.0002099878,0.00563055,0.0003708332,0.0000182402,0.00003456213,0.000007854384,0.0000170537,0.0002169277],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.602388,"threshold_uncertainty_score":0.7483526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01057071576771858,"score_gpt":0.2355505879691684,"score_spread":0.2249798722014499,"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."}}