{"paper":{"title":"Dynamic Programming for Epistemic Uncertainty in Markov Decision Processes","arxiv_id":"2602.03381","primary_cat":"cs.GT","submitted_at":"2026-02-03T11:01:43+00:00","version_compiled":"v2"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v2","sentences":[{"i":0,"p":0.94,"id":"s0","own":true,"role":"contribution","text":"In this paper, we propose a general theory of ambiguity-averse MDPs, which treats the uncertain transition probabilities as random variables and evaluates a policy via a risk measure applied to its random return.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.89,"main_claim_p":0.11,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.06,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.94,"interpretation":0.0}},{"i":1,"p":0.59,"id":"s1","own":true,"role":"contribution","text":"This ambiguity-averse MDP framework unifies several models of MDPs with epistemic uncertainty for specific choices of risk measures.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.62,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.17,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.59,"interpretation":0.23}},{"i":2,"p":0.7,"id":"s2","own":true,"role":"contribution","text":"We extend the concepts of value functions and Bellman operators to our setting.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.92,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.0,"method":0.3,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.7,"interpretation":0.0}},{"i":3,"p":0.66,"id":"s3","own":true,"role":"contribution","text":"Based on these objects, we establish the consequences of dynamic programming principles in this framework (existence of stationary policies, value and policy iteration algorithms), and we completely characterize law-invariant risk measures compatible with dynamic programming.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.39,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.34,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.66,"interpretation":0.0}},{"i":4,"p":0.5,"id":"s4","own":true,"role":"contribution","text":"Our work draws connections among several variants of MDP models and fully delineates what is possible under the dynamic programming paradigm and which risk measures require leaving it.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.58,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.15,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.5,"interpretation":0.35}}]},"compiled":{"main_claim":{"p":0.9,"text":"Our work draws connections among several variants of MDP models and fully delineates what is possible under the dynamic programming paradigm and which risk measures require leaving it.","location":"abstract s4","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":4280,"cost_usd_reported":0.0},"compiled_at":"2026-09-23","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.05,"states_limitation":0.55,"human_participants":0.02,"controlled_comparison":0.02,"randomized_assignment":0.01,"states_quantitative_result":0.04,"compares_with_prior_results":0.35,"mentions_code_or_data_availability":0.02},"evidential_basis":{"p":1.0,"value":"proof or derivation","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":1.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.0,"simulation_or_computation":0.0}},"contribution_type":{"p":0.99,"value":"theoretical result","probabilities":{"review":0.0,"method_or_tool":0.01,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.99,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.75,"text":"In this paper, we propose a general theory of ambiguity-averse MDPs, which treats the uncertain transition probabilities as random variables and evaluates a policy via a risk measure applied to its random return.","location":"abstract s0"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v2"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":5,"sentences_in_abstract":5},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448}}