Suchergebnisse

AbstractIn this paper we provide faster algorithms for approximately solving discounted Markov decision processes in multiple parameter regimes. Given a discounted Markov decision process (DMDP) with |S| states, |A| actions, discount factor γ ∈ (0, 1), and rewards in the range [−M, M], we show how to compute an ϵ‐optimal policy, with probability 1 − δ in time (Note: We use to hide polylogarithmic factors in the input parameters, that is, .) This contribution reflects the first nearly linear time, nearly linearly convergent algorithm for solving DMDPs for intermediate values of γ. We also show how to obtain improved sublinear time algorithms provided we can sample from the transition function in O(1) time. Under this assumption we provide an algorithm which computes an ϵ‐optimal policy for with probability 1 − δ in time Furthermore, we extend both these algorithms to solve finite horizon MDPs. Our algorithms improve upon the previous best for approximately computing optimal policies for fixed‐horizon MDPs in multiple parameter regimes. Interestingly, we obtain our results by a careful modification of approximate value iteration. We show how to combine classic approximate value iteration analysis with new techniques in variance reduction. Our fastest algorithms leverage further insights to ensure that our algorithms make monotonic progress towards the optimal value. This paper is one of few instances in using sampling to obtain a linearly convergent linear programming algorithm and we hope that the analysis may be useful more broadly.

How do we characterize and explain the behavioral patterns of the Chinese bureaucracy amid China's great transformation over the past three decades? The prevailing "tournament competition" model presented in the literature emphasizes the role of incentive design to explain bureaucratic behaviors. We develop an alternative model of "muddling through"-characterized by a reactive response to multiple pressures, constant readjustments and a focus on short-term gains-to explain the behavioral patterns of China's intermediate government agencies. We explain the underlying multiple bureaucratic logics that induce these behavioral patterns and the institutional conditions under which such behavioral patterns prevail. We illustrate the research issues, analytical concepts and theoretical arguments, using a case study of a municipal environmental protection bureau implementing the Five-Year Plan, between 2006 and 2010. (China J/GIGA)