{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001747386,0.0003844582,0.0004139887,0.00009348131,0.000669032,0.0002340428,0.0011015,0.0002141563,0.000009704749],"category_scores_gemma":[0.00004291855,0.0003194084,0.0002588856,0.0007027331,0.0001396714,0.0005119269,0.0002324216,0.0003661767,0.00002370606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00025712,"about_ca_system_score_gemma":0.0003445986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002889103,"about_ca_topic_score_gemma":0.000006200873,"domain_scores_codex":[0.9973384,0.00006133733,0.0003822234,0.0006303875,0.0006315403,0.0009561507],"domain_scores_gemma":[0.9983924,0.0002010009,0.0002943506,0.0007301154,0.0001589105,0.0002231952],"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":[0.0006372794,0.001583589,0.07198678,0.002085585,0.001951204,0.0004157939,0.04598809,0.7179612,0.008545307,0.05357751,0.06093299,0.03433468],"study_design_scores_gemma":[0.006307845,0.0007625503,0.006868277,0.0003650725,0.00007643607,0.0002944748,0.000282789,0.8307979,0.0009330115,0.0003331051,0.1515414,0.001437182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02167156,0.0001655338,0.9747264,0.0008194614,0.0003072151,0.0009765603,0.000007342823,0.0007337226,0.0005922179],"genre_scores_gemma":[0.5255514,0.0002164642,0.471502,0.000601685,0.0002338615,0.0001252094,0.0001007726,0.00007586934,0.001592744],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5038798,"threshold_uncertainty_score":0.9999258,"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."}}