Coordinating with different teammates is essential in cooperative multiagent systems (MASs). However, most multiagent reinforcement learning (MARL) methods assume fixed team compositions, which leads to agents overfitting their training partners and failing to cooperate well with different teams during the deployment phase. A common way to mitigate the problem is to anticipate teammate behaviors and adapt policies accordingly during cooperation. However, these methods use the same policy for both collecting information for modeling teammates and maximizing cooperation performance. We argue that these two goals may conflict and reduce the effectiveness of both. In this work, we propose coordinating with different teammates via team probing (CDP), a novel approach that rapidly adapts to different teams by disentangling probing and adaptation phases. Specifically, we first generate a diverse population of teams as training partners with a novel value-based diversity objective. Then, we train a probing module to probe and reveal the coordination pattern of each team with policy-dynamics reconstruction and get a representation space of the population. Finally, we train a generalist meta-policy consisting of several expert policies with module selection based on the clustering of the learned representation space. We empirically show that CDP surpasses existing policy adaptation methods in various complex multiagent scenarios with both seen and unseen teammates.

The phase-sensitive optical time-domain reflectometry (cp-OTDR) system can monitor the distribution of the acoustic field along the sensing fiber through single-ended access, making it applicable in various fields. However, phase fluctuation noise (PFN) suppression remains a significant challenge. This paper aims to clarify the complex relationship between the signal-to-noise ratio (SNR) of the intermediate frequency (IF) signal and PFN in cp-OTDR systems by quantitatively establishing the nonlinear relationship between the carrier-to-noise ratio (CNR) of the IF signal and the variance of the PFN (VPFN). Accordingly, we propose the MSI-VPFN algorithm, which effectively suppresses PFN by dynamically adjusting spatial weighting according to the standard deviation of VPFN. Compared to the original signal, applying the MSI-VPFN algorithm reduces the PFN standard deviation from 0.386 rad to 0.068 rad and decreases the probability of fading noise from 6.23% to 0.19%. The MSI-VPFN algorithm outperforms traditional methods, providing a scientific basis for evaluating system performance and establishing a solid foundation for the broader application of cp-OTDR technology.

Coordinating with previously unknown teammates without joint learning is a crucial need for real-world multi-agent applications, such as human-AI interaction. An active research topic on this problem is ad hoc teamwork, which improves agents' coordination ability in zero-shot settings. However, previous works can only solve the problem of a single agent's coordination with different teams, which is not in line with arbitrary group-to-group coordination in complex multi-agent scenarios. Moreover, they commonly suffer from limited adaptation ability within an episode in a zero-shot setting. To address these problems, we introduce the Coordination Scheme Probing (CSP) approach that applies a disentangled scheme probing module to represent and classify the newly arrived teammates beforehand with limited pre-collected episodic data and makes multi-agent control accordingly. To achieve generalization, CSP learns a meta-policy with multiple sub-policies that follow distinguished coordination schemes in an end-to-end fashion and automatically reuses it to coordinate with unseen teammates. Empirically, we show that the proposed method achieves remarkable performance compared to existing ad hoc teamwork and policy generalization methods in various multi-agent cooperative scenarios.

Multi-agent pathfinding (MAPF) is essential to large-scale robotic coordination tasks. Planning-based algorithms show their advantages in collision avoidance while avoiding exponential growth in the number of agents. Reinforcement-learning (RL)-based algorithms can be deployed efficiently but cannot prevent collisions entirely due to the lack of hard constraints. This paper combines the merits of planning-based and RL-based MAPF methods to propose a deployment-efficient and collision-free MAPF algorithm. The experiments show the effectiveness of our approach.