
Finding the Stochastic Shortest Path with Low Regret: The Adversarial Cost and Unknown Transition Case
We make significant progress toward the stochastic shortest path problem...
read it

Nearoptimal Regret Bounds for Stochastic Shortest Path
Stochastic shortest path (SSP) is a wellknown problem in planning and c...
read it

Minimax Regret for Stochastic Shortest Path with Adversarial Costs and Known Transition
We study the stochastic shortest path problem with adversarial costs and...
read it

Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
We propose two algorithms for episodic stochastic shortest path problems...
read it

Suboptimality Bounds for Stochastic Shortest Path Problems
We consider how to use the Bellman residual of the dynamic programming o...
read it

User Preferences and the Shortest Path
Indoor navigation systems leverage shortest path algorithms to calculate...
read it

The Faulty GPS Problem: Shortest Time Paths in Networks with Unreliable Directions
This paper optimizes motion planning when there is a known risk that the...
read it
Adversarial Stochastic Shortest Path
Stochastic shortest path (SSP) is a wellknown problem in planning and control, in which an agent has to reach a goal state in minimum total expected cost. In this paper we consider adversarial SSPs that also account for adversarial changes in the costs over time, while the dynamics (i.e., transition function) remains unchanged. Formally, an agent interacts with an SSP environment for K episodes, the cost function changes arbitrarily between episodes, and the fixed dynamics are unknown to the agent. We give high probability regret bounds of O (√(K)) assuming all costs are strictly positive, and O (K^3/4) for the general case. To the best of our knowledge, we are the first to consider this natural setting of adversarial SSP and obtain sublinear regret for it.
READ FULL TEXT
Comments
There are no comments yet.