The long-term safe storage of CO2 in geological reservoirs requires the understanding impact on clay-rich sealing cap rocks. reactivity mixed layer illite-smectite was investigated to determine reaction pathways under conditions supercritical (scCO2) context storage. A common clay (blue marl from Guadalquivir Tertiary basin, southern Spain) tested brine scCO2 (100 bar and 35 °C) for 120 240 h. ...

This paper develops an efficient multi-agent deep reinforcement learning algorithm for cooperative controls in powergrids. Specifically, we consider the decentralized inverter-based secondary voltage control problem distributed generators (DGs), which is first formulated as a (MARL) problem. We then propose novel on-policy MARL algorithm, PowerNet, each agent (DG) learns policy based on (sub-)g...

Abstract Knowledge transfer is widely adopted in accelerating multiagent reinforcement learning (MARL). To accelerate the speed of MARL for learning-from scratch agents, this paper, we propose a Stationary and Scalable knowledge approach based on Experience Sharing (S $$^{2}$$ 2 </mml:...

Model-free reinforcement learning (RL) techniques are currently drawing attention in the control of heating, ventilation, and air-conditioning (HVAC) systems due to their minor pre-conditions fast online optimization. The simultaneous optimal multiple HVAC appliances is a high-dimensional optimization problem, which single-agent RL schemes can barely handle. Hence, it necessary investigate how ...

The demand for autonomous UAV swarm operations has been on the rise following success of UAVs in various challenging tasks. Yet conventional control approaches are inadequate coping with scalability, computational requirements, and real-time performance. In this paper, we demonstrate capability emerging multi-agent reinforcement learning (MARL) to successfully efficiently make sequential decisi...

Tight marl is a special type of unconventional oil and gas resource, the study on its reservoir characteristics controlling factors immense scientific significance. In this paper, 113 core samples from Gouxi Area, Eastern Sichuan were selected. Based organic carbon, pyrolysis, X-ray diffraction whole rock, clay analysis, evaluation eyelid-shaped limestone in first member Maokou Formation was ca...

Multi-agent reinforcement learning (MARL) has become more and popular over recent decades, the need for high-level cooperation is increasing every day because of complexity real-world environment. However, multi-agent credit assignment problem that serves as main obstacle to coordination still not addressed properly. Though lots methods have been proposed, none them thought perform assignments ...

Expansive soils increase their volume upon wetting, but under high vertical stresses may exhibit collapse, with the latter aspect being rather overlooked in foundation engineering. Oedometer swelling/collapse tests on expansive Pliocene marls of various calcium carbonate content and plasticity index sampled from Nicosia, Cyprus, indicate that, unlike free swelling strain, pressure is insensitiv...