Surya Ramachandiran, Yiming Li, Juan Mancilla-Caceres, Tao Ye, Jun Liu · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26817 · open-access PDF
Próximo Os sistemas da NBA devem escolher entre intervenções do cliente (por exemplo, descontos, promoções e ações de ciclo de vida), maximizar o valor econômico a longo prazo, satisfazer restrições operacionais complexas e permanecer causalmente fundamentados. As abordagens existentes carecem de um quadro rigoroso para atender a esses requisitos em conjunto. Nós abordamos essa lacuna formulando a NBA como um Constrained Markov Decision Process (CMDP). Em seguida, integramos a correção causal fora da política da dinâmica estimada do cliente diretamente na formulação de Programação Linear (LP) do CMDP. A política resultante seleciona ações com base em
Machine translation (Meta M2M100); the English original follows.
Next Best Action (NBA) systems must select among customer interventions (e.g., discounts, promotions, and lifecycle actions), maximize long-term economic value, satisfy complex operational constraints, and remain causally grounded. Existing approaches lack a rigorous framework for meeting these requirements jointly. We address this gap by formulating NBA as a Constrained Markov Decision Process (CMDP). We then integrate off-policy causal correction of the estimated customer dynamics directly into the Linear Programming (LP) formulation of the CMDP. The resulting policy selects actions based on
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26817, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange