Multi-agent Reinforcement Learning (MARL) has been increasingly used in safety-critical applications but no safety guarantees, especially during training. In this paper, we propose dynamic shielding, a novel decentralized MARL framework to ensure both training and deployment phases. Our leverages Shield, reactive system running parallel with the reinforcement learning algorithm monitor correct ...

analyses and thermal infrared channels 4 and 5 NOAA- AVHRR images. This research was carried out in Lut Desert located in center of sub-tropical divergence dominant in' Iranian plateau. The physical and thermal properties of the various desert surfaces have been determined using correlation relationships between the desert variables including: dark sand, normal sand, marl, saline soil, soil dep...

In this paper, an integrated control framework is proposed for the optimization of production yield by integrating different levels a manufacturing system, including process, and machine levels. The system modeled as graph treating machines nodes material flows links. model enjoys high flexibility able to incorporate all relevant real-time information across in dynamic node feature. Since tool ...

Multi-Agent Reinforcement Learning (MARL) is widely used to solve various real-world problems. In MARL, the environment contains multiple agents. A good grasp of can guide agents learn cooperative strategies. Centralized Training Decentralized Execution (CTDE), a centralized critic strategies learning. However, having in leads curse dimensionality and influence other agents’ strategies, resulti...

Generally, the evaluation and assessment of the critical condition of rill formation are useful for a better understanding of soil erosion processes. The inherence characteristics of soils, which have much dynamic variations on the hillslopes and are affected by rill formation, are the soil critical shear stress and soil erodibility factors. This study aims to assess experimental rill incision ...

In the dynamic task allocation of unmanned underwater vehicles (UUVs), schemes UUVs need to be quickly reallocated respond emergencies. The most common heuristic method uses predesigned optimization rules iteratively obtain a solution, which is time-consuming. To assign tasks heterogeneous UUVs, we propose novel algorithm based on multi-agent reinforcement learning (MARL) and period training (P...

This paper investigates Multiagent Reinforcement Learning (MARL) in a general-sum game where the payoffs’ structure is such that the agents are required to exploit each other in a way that benefits all agents. The contradictory nature of these games makes their study in multiagent systems quite challenging. In particular, we investigate MARL with spiking and non-spiking agents in the Iterated P...