{"id":"W2108005621","doi":"10.1609/aaai.v26i1.8260","title":"Sample Bounded Distributed Reinforcement Learning for Decentralized POMDPs","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Computer science; Partially observable Markov decision process; Benchmark (surveying); Markov decision process; Bounded function; Mathematical optimization; Sample (material); Sample complexity; Computation; Set (abstract data type); Artificial intelligence; Markov process; Markov chain; Machine learning; Mathematics; Markov model; Algorithm","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":[0.0004417754,0.0002667707,0.0003327017,0.00008325469,0.0004338198,0.0005647899,0.001701603,0.0001063226,0.0001075393],"category_scores_gemma":[0.002544288,0.0002248286,0.0002155929,0.0007464603,0.0001412981,0.0003964819,0.0005447251,0.0003495697,0.00003398885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001276655,"about_ca_system_score_gemma":0.0002669535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000021069,"about_ca_topic_score_gemma":0.000002684176,"domain_scores_codex":[0.9974597,0.00002872364,0.0007477612,0.0005498042,0.0006409391,0.0005730993],"domain_scores_gemma":[0.997215,0.0003536957,0.0005566194,0.0003901932,0.001361598,0.000122845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005459266,0.00007596238,0.0002509268,0.00006753147,0.00004460881,5.188746e-7,0.0007218686,0.05549344,0.01185003,0.9256324,0.0001665229,0.005641578],"study_design_scores_gemma":[0.00008339699,0.0002036312,0.00006518222,0.0001337603,0.0000218013,0.000003331666,0.0002993447,0.6149811,0.3302173,0.05124858,0.002511909,0.0002306973],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006070271,0.00001805808,0.9882203,0.002346499,0.000480905,0.000534685,0.000004035773,0.00018177,0.002143484],"genre_scores_gemma":[0.9669596,0.00007698834,0.03217111,0.0001947182,0.00004744266,0.00005281055,0.00001249621,0.00001774967,0.0004670765],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9608893,"threshold_uncertainty_score":0.9168246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07689906790923026,"score_gpt":0.3054622507888089,"score_spread":0.2285631828795786,"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."}}