{"id":"W2162926979","doi":"10.1109/cdc.2009.5400662","title":"Arbitrarily modulated Markov decision processes","year":2009,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Transition (genetics); Computer science; Markov chain; Markov process; Markov model; Partially observable Markov decision process; Decision theory; Artificial intelligence; Mathematical optimization; Machine learning; Algorithm; Mathematics; Statistics","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":[0.0001254777,0.0001072662,0.00009934897,0.00008693699,0.00008069781,0.0002239362,0.0007604908,0.00005135753,0.00004795396],"category_scores_gemma":[0.0001577935,0.00008698116,0.00002785604,0.0005776967,0.00001196138,0.0005445632,0.00008345286,0.0001023654,0.0001536192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002124352,"about_ca_system_score_gemma":0.00007102646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003291203,"about_ca_topic_score_gemma":7.17113e-7,"domain_scores_codex":[0.9989679,0.00001281441,0.0001962385,0.0002603018,0.0003295947,0.0002330913],"domain_scores_gemma":[0.9992174,0.00008434383,0.00005461423,0.0004517823,0.0001187705,0.0000730883],"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":[0.00002239426,0.00009252623,0.0005599572,0.0000222554,0.00001649751,0.00003655406,0.0003516479,0.719919,0.001204165,0.04563451,0.008465862,0.2236746],"study_design_scores_gemma":[0.000310619,0.0002149455,0.007778431,0.00003428483,0.000002935063,0.00001477015,0.000004960154,0.9770653,0.002409251,0.008024156,0.003909141,0.0002312024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004544267,0.00003313495,0.9521947,0.0005933566,0.00013097,0.00009137448,5.038069e-8,0.0004029446,0.04200919],"genre_scores_gemma":[0.728215,0.00001427153,0.2685608,0.001139287,0.00002239202,0.000001026212,0.000001096721,0.000003727028,0.002042336],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7236708,"threshold_uncertainty_score":0.3546989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009695192704821434,"score_gpt":0.241276952183283,"score_spread":0.2315817594784616,"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."}}