{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004220793,0.001111926,0.001602364,0.0009804561,0.0008235096,0.003973485,0.001943477,0.002245515,0.002897158],"category_scores_gemma":[0.01192475,0.001013376,0.001129148,0.001942041,0.004265422,0.008801307,0.002347701,0.005326637,0.0004782394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002255476,"about_ca_system_score_gemma":0.002684784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004824779,"about_ca_topic_score_gemma":0.004392534,"domain_scores_codex":[0.9978501,0.001157478,0.0000871822,0.0002601971,0.0005120393,0.0001330105],"domain_scores_gemma":[0.9874611,0.01081997,0.0005534985,0.0003927493,0.0004906333,0.0002819552],"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":[0.00001398729,0.00004056818,0.000369557,0.0001861121,0.00002608325,0.00007268914,0.0001520298,0.05585402,0.00007069206,0.9230033,0.001929327,0.01828165],"study_design_scores_gemma":[0.00000533737,0.000008591668,0.00008246826,0.00004212613,0.000003453498,0.0000195422,0.00004528409,0.0977901,0.00003296537,0.8988727,0.003089792,0.000007716197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009952836,0.02477075,0.9322922,0.01758158,0.0002876598,0.00004925138,0.0001916107,0.0001298931,0.01474431],"genre_scores_gemma":[0.5078984,0.06287065,0.4122926,0.002308921,0.003222195,0.0004902516,0.0004121522,0.0001778212,0.01032694],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004824779,"threshold_uncertainty_score":0.022322,"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."}}