有限内存策略用于MDP中的几乎必然能量-平均收益目标
Finite-memory Strategies for Almost-sure Energy-MeanPayoff Objectives in MDPs
AI总结:
该研究针对有限状态马尔可夫决策过程中的能量-平均收益目标,证明有限内存足以实现几乎必然获胜策略,并给出指数内存的充分必要性及伪多项式时间可判定性。
摘要:
我们考虑具有组合能量-平均收益目标的有限状态马尔可夫决策过程。控制器试图避免能量耗尽,同时在第二个维度上实现严格正的平均收益。我们证明,对于能量-平均收益目标,有限内存足以实现几乎必然获胜的策略。这与密切相关的能量-奇偶目标形成对比,在能量-奇偶目标中,几乎必然获胜的策略通常需要无限内存。我们证明,对于几乎必然获胜的能量-平均收益,指数内存是充分的(即使对于确定性策略)且必要的(即使对于随机化策略)。即使将目标的严格正平均收益部分推广到多维严格正平均收益,上界仍然成立。最后,是否存在几乎必然获胜的策略可以在伪多项式时间内判定。
英文摘要:
We consider finite-state Markov decision processes with the combined Energy-MeanPayoff objective. The controller tries to avoid running out of energy while simultaneously attaining a strictly positive mean payoff in a second dimension. We show that finite memory suffices for almost surely winning strategies for the Energy-MeanPayoff objective. This is in contrast to the closely related Energy-Parity objective, where almost surely winning strategies require infinite memory in general. We show that exponential memory is sufficient (even for deterministic strategies) and necessary (even for randomized strategies) for almost surely winning Energy-MeanPayoff. The upper bound holds even if the strictly positive mean payoff part of the objective is generalized to multidimensional strictly positive mean payoff. Finally, it is decidable in pseudo-polynomial time whether an almost surely winning strategy exists.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。