2012/02/14 by Eric A. Hansen, Hansen, Eric A.
Computer Science · #Artificial Intelligence (cs.AI) #Bayesian Modeling and Causal Inference #FOS: Computer and information sciences #Machine Learning and Algorithms #Optimization and Search Problems #cs.AI
paper · pdf · doi:10.48550/arxiv.1202.3729
arxiv created 2012/02/14 · openalex publication_date 2012/02/14 · arxiv updated 2012/02/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We consider how to use the Bellman residual of the dynamic programming operator to compute suboptimality bounds for solutions to stochastic shortest path problems. Such bounds have been previously established only in the special case that "all policies are proper," in which case the dynamic programming operator is known to be a contraction, and have been shown to be easily computable only in the more limited special case of discounting. Under the condition that transition costs are positive, we show that suboptimality bounds can be easily computed even when not all policies are proper. In the general case when there are no restrictions on transition costs, the analysis is more complex. But we present preliminary results that show such bounds are possible.