{"id":"W233883780","doi":"10.1609/icaps.v21i1.13468","title":"Distributed Control of Situated Assistance in Large Domains with Many Tasks","year":2011,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Situated; Partially observable Markov decision process; Computer science; Task (project management); Scalability; Affordance; Domain (mathematical analysis); Set (abstract data type); Process (computing); Population; Markov decision process; Artificial intelligence; Human–computer interaction; Controller (irrigation); Control (management); Machine learning; Distributed computing; Markov process; Markov chain; Markov model; Engineering; Mathematics","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":[0.0003651433,0.0001299958,0.0001945929,0.0001138923,0.00006089384,0.00008872887,0.0008031152,0.00005948892,0.000006796332],"category_scores_gemma":[0.0001460052,0.0000939373,0.00002812886,0.0002472273,0.00006868883,0.0002544033,0.0001256062,0.0002207078,8.366731e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003204012,"about_ca_system_score_gemma":0.00004493906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001630684,"about_ca_topic_score_gemma":0.000001034478,"domain_scores_codex":[0.9988818,0.00001032187,0.0003241741,0.0002206547,0.0003779815,0.0001850591],"domain_scores_gemma":[0.9990369,0.00005212491,0.0004300161,0.0001000255,0.0003444144,0.00003652014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003884929,0.0001463065,0.477123,0.00009474195,0.0001813246,0.0000104392,0.00353941,0.05393176,0.01863169,0.4458118,0.00003369299,0.0001073286],"study_design_scores_gemma":[0.0008631716,0.0001012455,0.06763539,0.0007248343,0.000008366619,0.000007713636,0.0003151753,0.9241989,0.00560764,0.0004248504,0.000006432083,0.0001062377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8340549,0.00001725816,0.1611482,0.0002748168,0.00009493108,0.0001360342,0.00001267018,0.0001476917,0.004113434],"genre_scores_gemma":[0.9895632,0.000003875466,0.01033329,0.00005210815,0.000005701922,0.000005823756,0.000003225396,0.000006105443,0.00002667178],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8702672,"threshold_uncertainty_score":0.3830652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0298389820466585,"score_gpt":0.2599037297562931,"score_spread":0.2300647477096346,"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."}}