Sharif Digital Repository

Hierarchical reinforcement learning facilitates learning in large and complex domains by exploiting subtasks and creating hierarchical structures using these subtasks. Subtasks are usually defined through finding subgoals of the problem. Providing mechanisms for autonomous subgoal discovery and skill acquisition is a challenging issue in reinforcement learning. Among the proposed algorithms, a few of them are successful both in performance and also efficiency in terms of the running time of the algorithm. In this paper, we study four methods for subgoal discovery which are based on graph partitioning. The idea behind the methods proposed in this paper is that if we partition the transition... 

The hierarchical structure of real-world problems has resulted in a focus on hierarchical frameworks in the reinforcement learning paradigm. Preparing mechanisms for automatic discovery of macro-actions has mainly concentrated on subgoal discovery methods. Among the proposed algorithms, those based on graph partitioning have achieved precise results. However, few methods have been shown to be successful both in performance and also efficiency in terms of time complexity of the algorithm. In this paper, we present a SCC-based subgoal discovery algorithm; a graph theoretic approach for automatic detection of subgoals in linear time. Meanwhile a parameter tuning method is proposed to find the... 

This paper presents a new optimization-based approach to determine the class of stabilizing control structures with the necessary set of feedback links for interconnected systems. The proposed approach relies on a graph theoretic interpretation and its equivalence in terms of binary linear programs (BLP). To carry out the primary goal, first, the stabilizability of an LTI system under the decentralized control structure is presented in terms of a BLP. Next, two graph-based criteria are proposed to characterize stabilizing control structures with the required feedback links. Finally, all possible stabilizing control structures with the necessary feedback links are derived via solving a set of... 

This article presents a new optimization-based approach to determine the class of stabilizing control structures with the necessary set of feedback links for interconnected systems. The proposed approach relies on a graph-theoretic interpretation and its equivalence in terms of binary linear programs (BLPs). To carry out the primary goal, first, the stabilizability of a linear time-invariant (LTI) system under the decentralized control structure is presented in terms of a BLP. Next, two graph-based criteria are proposed to characterize stabilizing control structures with the required feedback links. Finally, all possible stabilizing control structures with the necessary feedback links are... 

Measurements and sensing implementations impose certain cost in sensor networks. The sensor selection cost optimisation is the problem of minimising the sensing cost of monitoring a physical (or cyber-physical) system. Consider a given set of sensors tracking states of a dynamical system for estimation purposes. For each sensor assume different costs to measure different (realisable) states. The idea is to assign sensors to measure states such that the global cost is minimised. The number and selection of sensor measurements need to ensure the observability to track the dynamic state of the system with bounded estimation error. The main question we address is how to select the state...