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...

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...

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...

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...