Sparse Stochastic Finite-State Controllers for POMDPs
This work addresses computational efficiency for researchers and practitioners in reinforcement learning and planning, but it is incremental as it builds on existing bounded policy iteration methods.
The paper tackled the scalability issue in bounded policy iteration for solving infinite-horizon POMDPs by developing a version that leverages the sparse structure of stochastic finite-state controllers, resulting in much better scalability while maintaining the same policy improvement per iteration.
Bounded policy iteration is an approach to solving infinite-horizon POMDPs that represents policies as stochastic finite-state controllers and iteratively improves a controller by adjusting the parameters of each node using linear programming. In the original algorithm, the size of the linear programs, and thus the complexity of policy improvement, depends on the number of parameters of each node, which grows with the size of the controller. But in practice, the number of parameters of a node with non-zero values is often very small, and does not grow with the size of the controller. Based on this observation, we develop a version of bounded policy iteration that leverages the sparse structure of a stochastic finite-state controller. In each iteration, it improves a policy by the same amount as the original algorithm, but with much better scalability.