A new polynomial-time algorithm for linear programming
Combinatorica
Journal of Computer and System Sciences
Dynamic programming: deterministic and stochastic models
Dynamic programming: deterministic and stochastic models
Combinatorial optimization: algorithms and complexity
Combinatorial optimization: algorithms and complexity
Parallel complexity theory
The complexity of Markov decision processes
Mathematics of Operations Research
Parallel and distributed computation: numerical methods
Parallel and distributed computation: numerical methods
Progress in Mathematical Programming Interior-point and related methods
Progress in Mathematical Programming Interior-point and related methods
Computers and Intractability: A Guide to the Theory of NP-Completeness
Computers and Intractability: A Guide to the Theory of NP-Completeness
The complexity of dynamic languages and dynamic optimization problems
STOC '81 Proceedings of the thirteenth annual ACM symposium on Theory of computing
Reachability analysis of uncertain systems using bounded-parameter Markov decision processes
Artificial Intelligence
Planning and acting in partially observable stochastic domains
Artificial Intelligence
Survey A survey of computational complexity results in systems and control
Automatica (Journal of IFAC)
Parallel Abductive Query Answering in Probabilistic Logic Programs
ACM Transactions on Computational Logic (TOCL)
Hi-index | 0.00 |
We consider the H-horizon, stationary Markov decision problem. For the discounted case, we give an @e-approximation algorithm whose time is proportional to log(1/@e), log(H) and1(1 - @a). For problems where @a is bounded away from 1, we obtain, respectively, a fully polynomial approximation scheme and a polynomial-time algorithm. For the undiscounted case, by refining a weighted maximum norm contraction result of Hoffman, we derive analogous results under the assumption that all stationary policies are proper.