Learning-Based Multi-UAV Flocking Control With Limited Visual Field and Instinctive Repulsion

This article explores deep reinforcement learning (DRL) for the flocking control of unmanned aerial vehicle (UAV) swarms. The flocking control policy is trained using a centralized-learning-decentralized-execution (CTDE) paradigm, where a centralized critic network augmented with additional information about the entire UAV swarm is utilized...

Automatic enhancement of vascular configuration for self-healing concrete through reinforcement learning approach

Vascular self-healing concrete (SHC) has great potential to mitigate the environmental impact of the construction industry by increasing the durability of structures. Designing concrete with high initial mechanical properties by searching a specific arrangement of vascular structure is of great importance. Herein, an automatic optimization...

Timeslot allocation for waiting list control: Tactical planning of orthopaedic surgeons at the Sint Maartenskliniek

Patients visiting a hospital for elective surgery often have multiple consultations with a surgeon before undergoing surgery. Hospitals discern between different types of consultations, and make a schedule allocating timeslots of outpatient department sessions to these different consultation types several weeks in advance. Changing the...

Learning Tracking Control for Cyber-Physical Systems

This paper investigates the problem of optimal tracking control for cyber-physical systems (CPS) when the cyber realm is attacked by denial-of-service (DoS) attacks which can prevent the control signal transmitting to the actuator. Attention is focused on how to design the optimal tracking control scheme without using the system dynamics and...

Machine Learning in Chemical Engineering: A Perspective

The transformation of the chemical industry to renewable energy and feedstock supply requires new paradigms for the design of flexible plants, (bio-)catalysts, and functional materials. Recent breakthroughs in machine learning (ML) provide unique opportunities, but only joint interdisciplinary research between the ML and chemical engineering ...

Learning Optimal Controllers for Linear Systems with Multiplicative Noise via Policy Gradient

The linear quadratic regulator (LQR) problem has reemerged as an important theoretical benchmark for reinforcement learning-based control of complex dynamical systems with continuous state and action spaces. In contrast with nearly all recent work in this area, we consider multiplicative noise models, which are increasingly relevant because...

Symbolic Regression Methods for Reinforcement Learning

Reinforcement learning algorithms can solve dynamic decision-making and optimal control problems. With continuous-valued state and input variables, reinforcement learning algorithms must rely on function approximators to represent the value function and policy mappings. Commonly used numerical approximators, such as neural networks or basis...

Optimizing Edge Computing in 5G Networks

Multi-access Edge Computing (MEC) is a concept brought up by ETSI and it places computing, storage, processing and network resources into MEC hosts and places these MEC hosts as close as needed to the telecom network edge in order to reduce service latency and bandwidth usage. For self-driving vehicles, streaming video and real-time gaming, the...

Fine-tuning deep RL with gradient-free optimization

Deep reinforcement learning makes it possible to train control policies that map high-dimensional observations to actions. These methods typically use gradient-based optimization techniques to enable relatively efficient learning, but are notoriously sensitive to hyperparameter choices and do not have good convergence properties. Gradient...

Resource-constrained Multi-agent Markov Decision Processes

Intelligent autonomous agents, designed to automate and simplify many aspects of our society, will increasingly be required to also interact with other agents autonomously. Where agents interact, they are likely to encounter resource constraints. For example, agents managing household appliances to optimize electricity usage might need to share...

Policy derivation methods for critic-only reinforcement learning in continuous spaces

This paper addresses the problem of deriving a policy from the value function in the context of critic-only reinforcement learning (RL) in continuous state and action spaces. With continuous-valued states, RL algorithms have to rely on a numerical approximator to represent the value function. Numerical approximation due to its nature virtually...

Reinforcement learning for control: Performance, stability, and deep approximators

Reinforcement learning (RL) offers powerful algorithms to search for optimal controllers of systems with nonlinear, possibly stochastic dynamics that are unknown or highly uncertain. This review mainly covers artificial-intelligence approaches to RL, from the viewpoint of the control engineer. We explain how approximate representations of the...

Benchmarking model-free and model-based optimal control

Model-free reinforcement learning and nonlinear model predictive control are two different approaches for controlling a dynamic system in an optimal way according to a prescribed cost function. Reinforcement learning acquires a control policy through exploratory interaction with the system, while nonlinear model predictive control exploits an...