activity
20162020
most citedPolicy Learning of MDPs with Mixed Continuous/Discrete Variables: A Case Study on Model-Free Control of Markovian Jump Systems

5 citations · 5 across the 5 of their papers we have counts for

collaborators

5 papers

math.OC2020

Verifying Stochastic Hybrid Systems with Temporal Logic Specifications via Model Reduction

Yu Wang, Nima Roohi, Matthew West +2

We present a scalable methodology to verify stochastic hybrid systems. Using the Mori-Zwanzig reduction method, we construct a finite state Markov chain reduction of a given stocha…

math.OC20205 cited

Policy Learning of MDPs with Mixed Continuous/Discrete Variables: A Case Study on Model-Free Control of Markovian Jump Systems

Joao Paulo Jansch-Porto, Bin Hu, Geir Dullerud

Markovian jump linear systems (MJLS) are an important class of dynamical systems that arise in many control applications. In this paper, we introduce the problem of controlling unk…

math.OC2020

Convergence Guarantees of Policy Optimization Methods for Markovian Jump Linear Systems

Joao Paulo Jansch-Porto, Bin Hu, Geir Dullerud

Recently, policy optimization for control purposes has received renewed attention due to the increasing interest in reinforcement learning. In this paper, we investigate the conver…

cs.RO2019

CyPhyHouse: A Programming, Simulation, and Deployment Toolchain for Heterogeneous Distributed Coordination

Ritwika Ghosh, Joao P. Jansch-Porto, Chiao Hsieh +6

Programming languages, libraries, and development tools have transformed the application development processes for mobile computing and machine learning. This paper introduces the…

math.DS2016

Extremal storage functions and minimal realizations of discrete-time linear switching systems

Matthew Philippe, Ray Essick, Geir Dullerud +1

We study the induced gain of discrete-time linear switching systems with graph-constrained switching sequences. We first prove that, for stable systems in a minimal…