{"id":"W1978322215","doi":"10.1109/tcyb.2014.2375817","title":"Energy Efficient Execution of POMDP Policies","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Research, Innovation and Science; Toronto Rehabilitation Institute; Alzheimer's Association","keywords":"Partially observable Markov decision process; Computer science; Benchmark (surveying); Markov decision process; Compiler; Mathematical optimization; Markov chain; Markov process; Machine learning; Markov model","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001561439,0.0001410926,0.0001520471,0.0002007597,0.00006606294,0.00005027304,0.0004801441,0.00008211444,0.000009921425],"category_scores_gemma":[0.000007870532,0.0001399689,0.00008128105,0.0004341504,0.00008825055,0.00009078818,0.00000528158,0.0001365416,0.00003233369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009485169,"about_ca_system_score_gemma":0.0001082803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001474869,"about_ca_topic_score_gemma":0.000009037562,"domain_scores_codex":[0.9986845,0.00005892422,0.0002970306,0.0002094618,0.0005096042,0.0002405132],"domain_scores_gemma":[0.9989706,0.00007699661,0.0001171186,0.000524805,0.0001744109,0.0001360505],"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":[0.000007162373,0.00008372387,0.000003908674,0.000004306137,0.00001509356,0.000001369043,0.0007216629,0.9812284,0.0004712603,0.01179128,0.0002106584,0.005461144],"study_design_scores_gemma":[0.0004069851,0.0003672224,0.00006454976,0.0000241532,0.00001790127,0.00001045732,0.00006086743,0.9334537,0.06256986,0.0002597632,0.002588171,0.0001763382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004811856,0.00002865039,0.9890832,0.0002172362,0.000848197,0.0000708987,0.000003942769,0.0001280012,0.00480804],"genre_scores_gemma":[0.9865507,0.00002533266,0.01188977,0.0001323729,0.00002561498,0.00000651847,0.000001007615,0.00001240625,0.001356271],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9817389,"threshold_uncertainty_score":0.5707766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02732000776719214,"score_gpt":0.2497968533708466,"score_spread":0.2224768456036544,"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."}}