Stochastic Shortest Path with Adversarially Changing Costs
Stochastic Shortest Path with Adversarially Changing Costs
Aviv Rosenberg, Yishay Mansour
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Main Track. Pages 2936-2942.
https://doi.org/10.24963/ijcai.2021/404
Stochastic shortest path (SSP) is a well-known problem in planning and control, in which an agent has to reach a goal state in minimum total expected cost. In this paper we present the adversarial SSP model that also accounts for adversarial changes in the costs over time, while the underlying transition function remains unchanged. Formally, an agent interacts with an SSP environment for K episodes, the cost function changes arbitrarily between episodes, and the transitions are unknown to the agent. We develop the first algorithms for adversarial SSPs and prove high probability regret bounds of square-root K assuming all costs are strictly positive, and sub-linear regret in the general case. We are the first to consider this natural setting of adversarial SSP and obtain sub-linear regret for it.
Keywords:
Machine Learning: Online Learning
Machine Learning: Reinforcement Learning