State aggregation for distributed value iteration in dynamic programming
We propose a distributed algorithm to solve a dynamic programming problem with multiple agents, where each agent has only partial knowledge of the state transition probabilities and costs. We provide consensus proofs for the presented algorithm and derive error bounds of the obtained value function...
| Glavni autori: | , |
|---|---|
| Format: | Journal article |
| Jezik: | English |
| Izdano: |
IEEE
2023
|