{"id":"W2121943493","doi":"","title":"Exact Dynamic Programming for decentralized POMDPs with lossless policy compression","year":2008,"lang":"en","type":"article","venue":"MPG.PuRe (Max Planck Society)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Benchmark (surveying); Curse of dimensionality; Dynamic programming; Mathematical optimization; State space; Reinforcement learning; Lossless compression; Partially observable Markov decision process; Markov decision process; Computation; Compression (physics); State (computer science); Theoretical computer science; Artificial intelligence; Data compression; Algorithm; Machine learning; Mathematics; Markov process; Markov chain; Markov model","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001183423,0.0008363744,0.001410614,0.0004597474,0.0003705105,0.001046354,0.001015756,0.001069408,0.003209513],"category_scores_gemma":[0.004583065,0.0005925569,0.0005663967,0.0007891633,0.0008679801,0.001929286,0.001834621,0.001920469,0.00042358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009969026,"about_ca_system_score_gemma":0.001399141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00255838,"about_ca_topic_score_gemma":0.002721576,"domain_scores_codex":[0.999453,0.0001634475,0.00003185645,0.00009983488,0.0001783781,0.0000734971],"domain_scores_gemma":[0.9985883,0.00101179,0.00009985662,0.0001510327,0.000100772,0.00004822808],"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":[0.0000498527,0.00002630254,0.0001001424,0.00005344891,0.00001491064,0.00002102352,0.00002276608,0.9494566,0.0003371516,0.0236695,0.0007467049,0.02550156],"study_design_scores_gemma":[0.00000778355,0.000008540303,0.00001457403,0.000003031824,0.000001719522,0.000003285833,0.000001889924,0.9863067,0.0001203057,0.01336455,0.0001659032,0.00000161951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008836369,0.0001798631,0.9880634,0.0002106283,0.00003854674,0.00004414418,0.00009538527,0.0002627613,0.002268843],"genre_scores_gemma":[0.6910134,0.0004056777,0.3007345,0.0002222753,0.0001048453,0.0004934812,0.0003791094,0.0001671411,0.006479529],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003209513,"threshold_uncertainty_score":0.01073682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01632395419192753,"score_gpt":0.2640261816231664,"score_spread":0.2477022274312389,"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."}}