论文标题
马尔可夫风险措施中对风险敏感的马尔可夫决策问题建模的鲁棒性
Robustness to Modeling Errors in Risk-Sensitive Markov Decision Problems with Markov Risk Measures
论文作者
论文摘要
我们考虑对风险敏感的马尔可夫决策过程（MDP），其中MDP模型受到在紧凑型公制空间中值的参数的影响。我们确定了足够的条件，在该条件下，模型参数中的小扰动会导致最佳价值函数和最佳策略的小变化。我们进一步建立了对建模错误的风险敏感最佳政策的鲁棒性。讨论了结果对数据驱动的决策，具有优先不确定性的决策以及噪声分布不断变化的系统的影响。
We consider risk-sensitive Markov decision processes (MDPs), where the MDP model is influenced by a parameter which takes values in a compact metric space. We identify sufficient conditions under which small perturbations in the model parameters lead to small changes in the optimal value function and optimal policy. We further establish the robustness of the risk-sensitive optimal policies to modeling errors. Implications of the results for data-driven decision-making, decision-making with preference uncertainty, and systems with changing noise distributions are discussed.
