Frank L. Lewis

Chenyuan He, Yan Wan, Frank L. Lewis

The influence model is a discrete-time stochastic model that succinctly captures the interactions of a network of Markov chains. The model produces a reduced-order representation of the stochastic network, and can be used to describe and tractably analyze probabilistic spatiotemporal spread dynamics, and hence has found broad usage in network applications such as social networks, traffic management, and failure cascades in power systems. This paper provides sufficient and necessary conditions for the identifiability of the influence model, and also develops estimators for the model structure through exploiting the model's special properties. In addition, we analyze conditions for the identifiability of the partially observed influence model (POIM), for which not all of the sites can be measured.

Wenqian Xue, Bosen Lian, Jialu Fan et al.

In this paper, we formulate inverse reinforcement learning (IRL) as an expert-learner interaction whereby the optimal performance intent of an expert or target agent is unknown to a learner agent. The learner observes the states and controls of the expert and hence seeks to reconstruct the expert's cost function intent and thus mimics the expert's optimal response. Next, we add non-cooperative disturbances that seek to disrupt the learning and stability of the learner agent. This leads to the formulation of a new interaction we call zero-sum game IRL. We develop a framework to solve the zero-sum game IRL problem that is a modified extension of RL policy iteration (PI) to allow unknown expert performance intentions to be computed and non-cooperative disturbances to be rejected. The framework has two parts: a value function and control action update based on an extension of PI, and a cost function update based on standard inverse optimal control. Then, we eventually develop an off-policy IRL algorithm that does not require knowledge of the expert and learner agent dynamics and performs single-loop learning. Rigorous proofs and analyses are given. Finally, simulation experiments are presented to show the effectiveness of the new approach.

Shimin Wang, Xiangyu Meng, Hongwei Zhang et al.

Knowledge-based leader-following synchronization of heterogeneous nonlinear multi-agent systems is a challenging problem since the leader's dynamic information is unknown to any follower node. This paper proposes a learning-based fully distributed observer for a class of nonlinear leader systems, which can simultaneously learn the leader's dynamics and states. This class of leader dynamics is rather general and does not require a bounded Jacobian matrix. Based on this learning-based distributed observer, we further synthesize an adaptive distributed control law for solving the leader-following synchronization problem of multiple Euler-Lagrange systems subject to an uncertain nonlinear leader system. The results are illustrated by a simulation example.

Mohammed Abouheaf, Wail Gueaieb, Frank Lewis

The control problem of the flexible wing aircraft is challenging due to the prevailing and high nonlinear deformations in the flexible wing system. This urged for new control mechanisms that are robust to the real-time variations in the wing's aerodynamics. An online control mechanism based on a value iteration reinforcement learning process is developed for flexible wing aerial structures. It employs a model-free control policy framework and a guaranteed convergent adaptive learning architecture to solve the system's Bellman optimality equation. A Riccati equation is derived and shown to be equivalent to solving the underlying Bellman equation. The online reinforcement learning solution is implemented using means of an adaptive-critic mechanism. The controller is proven to be asymptotically stable in the Lyapunov sense. It is assessed through computer simulations and its superior performance is demonstrated on two scenarios under different operating conditions.

Patrik Kolaric, Devesh K. Jha, Arvind U. Raghunathan et al.

The goal of this paper is to present a method for simultaneous trajectory and local stabilizing policy optimization to generate local policies for trajectory-centric model-based reinforcement learning (MBRL). This is motivated by the fact that global policy optimization for non-linear systems could be a very challenging problem both algorithmically and numerically. However, a lot of robotic manipulation tasks are trajectory-centric, and thus do not require a global model or policy. Due to inaccuracies in the learned model estimates, an open-loop trajectory optimization process mostly results in very poor performance when used on the real system. Motivated by these problems, we try to formulate the problem of trajectory optimization and local policy synthesis as a single optimization problem. It is then solved simultaneously as an instance of nonlinear programming. We provide some results for analysis as well as achieved performance of the proposed technique under some simplifying assumptions.

Sami El-Ferik, Bilal A. Siddiqui, Frank L. Lewis

This is an extended version of a technical note accepted for publication in IEEE Transactions on Automatic Control. The note proposes an Input to State practically Stable (ISpS) formulation of distributed nonlinear model predictive controller (NMPC) for formation control of constrained autonomous vehicles in presence of communication bandwidth limitation and transmission delays. Planned trajectories are compressed using neural networks resulting in considerable reduction of data packet size, while being robust to propagation delays and uncertainty in neighbors' trajectories. Collision avoidance is achieved by means of spatially filtered potential field. Analytical results proving ISpS and generalized small gain conditions are presented for both strongly- and weakly-connected networks, and illustrated by simulations.