{"id":"W176737593","doi":"","title":"Planning and programming with first-order markov decision processes: insights and challenges","year":2001,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov decision process; Bellman equation; Computer science; Dynamic programming; Mathematical optimization; State space; Representation (politics); Markov process; Automated planning and scheduling; State (computer science); Function (biology); Markov chain; Mathematics; Artificial intelligence; Algorithm; Machine learning","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":[0.0001103175,0.0001338522,0.000117095,0.0000914619,0.0001864392,0.0002869838,0.0002231573,0.00004606538,0.000003480227],"category_scores_gemma":[0.00009146481,0.00009217099,0.000005560048,0.0002955431,0.00004889751,0.0005911308,0.0002080704,0.00008839157,0.000002655999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009459642,"about_ca_system_score_gemma":0.00003763438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005662496,"about_ca_topic_score_gemma":0.00004987054,"domain_scores_codex":[0.999057,0.00001199861,0.0001305423,0.000342431,0.0002408542,0.0002171622],"domain_scores_gemma":[0.9992909,0.0002466534,0.00005852007,0.0002200147,0.00009796616,0.00008589698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001298701,0.0001129802,0.06295986,0.001061784,0.00008051481,0.0003219718,0.0246191,0.08873014,0.00001084532,0.01737579,0.0002095344,0.8043876],"study_design_scores_gemma":[0.002481096,0.001847458,0.02674467,0.001498091,0.00002902093,0.0006357,0.002132908,0.7198423,0.00008434456,0.001114137,0.2424404,0.001149965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01235684,0.003535132,0.9790482,0.0006675288,0.00003160967,0.0001806974,1.361722e-8,0.0001602976,0.00401971],"genre_scores_gemma":[0.4673993,0.003563252,0.5284293,0.0001130447,0.00002921516,0.00001838569,6.074147e-7,0.0000138053,0.0004330891],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8032377,"threshold_uncertainty_score":0.3758624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02615278811115168,"score_gpt":0.2471596119159763,"score_spread":0.2210068238048246,"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."}}