5 papers
Structure Matters: Dynamic Policy Gradient
Sara Klein, Xiangyuan Zhang, Tamer Başar +2
In this work, we study -discounted infinite-horizon tabular Markov decision processes (MDPs) and introduce a framework called dynamic policy gradient (DynPG). The framework dire…
Decision Transformer as a Foundation Model for Partially Observable Continuous Control
Xiangyuan Zhang, Weichao Mao, Haoran Qiu +1
Closed-loop control of nonlinear dynamical systems with partial-state observability demands expert knowledge of a diverse, less standardized set of theoretical tools. Moreover, it…
Policy Optimization for PDE Control with a Warm Start
Xiangyuan Zhang, Saviz Mowlavi, Mouhacine Benosman +1
Dimensionality reduction is crucial for controlling nonlinear partial differential equations (PDE) through a "reduce-then-design" strategy, which identifies a reduced-order model a…
Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms
Xiangyuan Zhang, Weichao Mao, Saviz Mowlavi +2
We introduce controlgym, a library of thirty-six industrial control settings, and ten infinite-dimensional partial differential equation (PDE)-based control problems. Integrated wi…
Global Convergence of Receding-Horizon Policy Search in Learning Estimator Designs
Xiangyuan Zhang, Saviz Mowlavi, Mouhacine Benosman +1
We introduce the receding-horizon policy gradient (RHPG) algorithm, the first PG algorithm with provable global convergence in learning the optimal linear estimator designs, i.e.,…