11 papers
Context-Triggered Robust MPC for Temporal Logic Specifications
Arash Bahari Kordabad, Satya Prakash Nayak, Sadegh Soudjani +1
We consider the problem of synthesizing robust feedback controllers for discrete-time linear systems that ensure the satisfaction of context-dependent linear temporal logic specifi…
Multi-Agent Temporal Logic Planning via Penalty Functions and Block-Coordinate Optimization
Eleftherios E. Vlahakis, Arash Bahari Kordabad, Lars Lindemann +3
Multi-agent planning under Signal Temporal Logic (STL) is often hindered by collaborative tasks that lead to computational challenges due to the inherent high dimensionality of the…
Almost Sure Reachability in Continuous-time Stochastic Systems
Arash Bahari Kordabad, Rupak Majumdar, Sadegh Soudjani
We provide certificates for almost sure reachability of continuous-time stochastic systems governed by stochastic differential equations (SDEs). We first show that a standard Euler…
Quasi-Newton Compatible Actor-Critic for Deterministic Policies
Arash Bahari Kordabad, Dean Brandner, Sebastien Gros +2
In this paper, we propose a second-order deterministic actor-critic framework in reinforcement learning that extends the classical deterministic policy gradient method to exploit c…
Second-Order Policy Gradient Methods for the Linear Quadratic Regulator
Amirreza Valaei, Arash Bahari Kordabad, Sadegh Soudjani
Policy gradient methods are a powerful family of reinforcement learning algorithms for continuous control that optimize a policy directly. However, standard first-order methods oft…
Sum-of-Squares Certificates for Almost-Sure Reachability of Stochastic Polynomial Systems
Arash Bahari Kordabad, Rupak Majumdar, Sadegh Soudjani
In this paper, we present a computational approach to certify almost sure reachability for discrete-time polynomial stochastic systems by turning drift--variant criteria into sum-o…