# Can the solution to a POMDP be found using linear programming?

It is known that Markov decision processes (MDPs) can be solved using linear programming (see page 24 of Carlos Guestrin's PhD dissertation). The linear program is:

$$min_{V(x)} \sum_x \alpha(x)V(x)\\ \text{subject to: } V(x) \ge R(x,a) + \gamma\sum_{x'}P(x'|x,a)V(x')\text{ for all }x\in X, a\in A$$

where $V(x)$ is the value of starting at state $x$ (note that $V(x)$ is the decision variable), parameters $\alpha(x)>0$ for all $x$ which are termed state relevance weights and are typically normalized, that is $\sum_x\alpha(x)=1$ (the solution of the above LP is actually, surprisingly, independent of the exact choice of $\alpha$), $R(x,a)$ is the reward obtained in state $x$ when action $a$ is taken, and $P(x'|x,a)$ is the probability that transition to state $x'$ when we take action $a$ in state $x$.

Question: does anyone know of a similar linear programming formulation for solving partially observable Markov decision processes (POMDPs)?

• Not an answer, but one thing is that the state variable $x$ is finite in an MDP. In a POMDP, the value function depends on the belief state which lives in an infinite-dimensional space. This complicates the extension to the POMDP setting. Jan 1, 2016 at 6:26