Search

Multi-agent reinforcement learning (MARL) has demonstrated significant potential in enabling cooperative agents. The communication protocol, which is responsible for message exchange between agents, is crucial in cooperation. However, communicative MARL systems still face challenges due to the noisy messages in complex multi-agent decision processes. This issue often stems from the entangled representation of observations and messages in policy networks. To address this, we propose the Message Action Adapter Framework (MAAF), which first trains individual agents without message inputs and then adapts a residual action based on message components. This separation isolates the effect of messages on action inference. We explore how training the MAAF framework with model-agnostic message types and varying optimization strategies influences adaptation performance. The experimental results indicate that MAAF achieves competitive performance across multiple baselines despite utilizing only half of the available communication, and shows an average improvement of 7.6% over the full attention-based communication approach. Additional findings suggest that different message types result in significant performance variations, emphasizing the importance of environment-specific message types. We demonstrate how the proposed architecture separates communication channels, effectively isolating message contributions.

Polyvinylidene fluoride (PVDF) dual-layer hollow fiber membranes were simultaneously fabricated by thermally induced phase separation (TIPS) and non-solvent induced phase separation (NIPS) methods using a triple orifice spinneret (TOS) for water treatment application. The support layer was prepared from a TIPS dope solution, which was composed of PVDF, gamma-butyrolactone (GBL), and N-methyl-2-pyrrolidone (NMP). The coating layer was prepared from a NIPS dope solution, which was composed of PVDF, N,N-dimethylacetamide (DMAc), and polyvinylpyrrolidone (PVP). In order to improve the mechanical strength of the dual-layer hollow fiber, a nucleating agent, sodium 2,2′-methylene bis-(4,6-di-tert-butylphenyl) phosphate (NA11), was added to the TIPS dope solution. The performance of the membrane was evaluated by surface and cross-sectional morphology, water flux, mechanical strength, and thermal property. Our results demonstrate that NA11 improved the mechanical strength of the PVDF dual-layer hollow fiber membranes by up to 42%. In addition, the thickness of the coating layer affected the porosity of the membrane and mechanical performance to have high durability in enduring harsh processing conditions.

This paper deals with the concept of multi-robot task allocation, referring to the assignment of multiple robots to tasks such that an objective function is maximized. The performance of existing meta-heuristic methods worsens as the number of robots or tasks increases. To tackle this problem, a novel Markov decision process formulation for multi-robot task allocation is presented for reinforcement learning. The proposed formulation sequentially allocates robots to tasks to minimize the total time taken to complete them. Additionally, we propose a deep reinforcement learning method to find the best allocation schedule for each problem. Our method adopts the cross-attention mechanism to compute the preference of robots to tasks. The experimental results show that the proposed method finds better solutions than meta-heuristic methods, especially when solving large-scale allocation problems.

Recently, the use of quadrotors has increased in numerous applications, such as agriculture, rescue, transportation, inspection, and localization. Time-optimal quadrotor waypoint tracking is defined as controlling quadrotors to follow the given waypoints as quickly as possible. Although PID control is widely used for quadrotor control, it is not adaptable to environmental changes, such as various trajectories and dynamic external disturbances. In this work, we discover that adjusting PID control frequencies is necessary for adapting to environmental changes by showing that the optimal control frequencies can be different for different environments. Therefore, we suggest a method to schedule the PID position and attitude control frequencies for time-optimal quadrotor waypoint tracking. The method includes (1) a Control Frequency Agent (CFA) that finds the best control frequencies in various environments, (2) a Quadrotor Future Predictor (QFP) that predicts the next state of a quadrotor, and (3) combining the CFA and QFP for time-optimal quadrotor waypoint tracking under unknown external disturbances. The experimental results prove the effectiveness of the proposed method by showing that it reduces the travel time of a quadrotor for waypoint tracking.

This paper analyzes how over-coupled coils affect odd harmonic current and electromagnetic interference (EMI) in a wireless power transfer (WPT) system, and proposes design considerations for series inductors to solve the EMI problem. When the air gap of the coils of the WPT system decreases below a certain level and the coils are over-coupled, the odd harmonic component of the input impedance of the system decreases and odd harmonic currents increase. The increase in the odd harmonic components current quickly aggravates the EMI issues. To solve the EMI problem of the over-coupled WPT system, additional series inductors were applied to the system, and considerations for designing the series inductors were analyzed. When designing additional series inductors, power transfer efficiency, maximum power transfer, input impedance and odd harmonic components current must be considered. Using simulations and experiments, it was confirmed that the WPT system designed with analyzed considerations maintained relatively high efficiency and reduced EMI issues.