Adversarial Stochastic Shortest Path

06/20/2020
by   Aviv Rosenberg, et al.
0

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 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 sub-linear regret for it.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/10/2021

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...
research
02/23/2020

Near-optimal Regret Bounds for Stochastic Shortest Path

Stochastic shortest path (SSP) is a well-known problem in planning and c...
research
12/29/2022

Graph Searching with Predictions

Consider an agent exploring an unknown graph in search of some goal stat...
research
12/07/2020

Minimax Regret for Stochastic Shortest Path with Adversarial Costs and Known Transition

We study the stochastic shortest path problem with adversarial costs and...
research
10/18/2018

Planning in Stochastic Environments with Goal Uncertainty

We present the Goal Uncertain Stochastic Shortest Path (GUSSP) problem -...
research
07/23/2021

User Preferences and the Shortest Path

Indoor navigation systems leverage shortest path algorithms to calculate...
research
10/17/2022

A Unified Algorithm for Stochastic Path Problems

We study reinforcement learning in stochastic path (SP) problems. The go...

Please sign up or login with your details

Forgot password? Click here to reset