Mean field games (MFGs) have emerged as a powerful framework for modeling interactions in large-scale multi-agent systems. Despite recent advancements in reinforcement learning (RL) for MFGs, existing methods are typically limited to finite spaces or stationary models, hindering their applicability to real-world problems. This paper introduces a novel deep reinforcement learning (DRL) algorithm specifically designed for non-stationary continuous MFGs. The proposed approach builds upon a Fictitious Play (FP) methodology, leveraging DRL for best-response computation and supervised learning for average policy representation. Furthermore, it learns a representation of the time-dependent population distribution using a Conditional Normalizing Flow. To validate the effectiveness of our method, we evaluate it on three different examples of increasing complexity. By addressing critical limitations in scalability and density approximation, this work represents a significant advancement in applying DRL techniques to complex MFG problems, bringing the field closer to real-world multi-agent systems.

This work explores a new concept of operations for observation of Earth events by a satellite sensor web that is able to reason about its capabilities and plan observations based on detected or requested events on Earth’s surface. An intelligent agile satellite sensor web is shown to produce more than twice the number of observations of a nadir-looking sensor web.

Monitoring of short-lived and highly-dynamic processes and events such as floods or forest fires has gained an increasing interest in Earth Observation, particularly as global climate change is affecting these processes. The observation of such dynamic events is often limited by the response time of human operation of Earth-Observing satellites or UAVs.To address this bottleneck, this paper presents a Modified Asynchronous Consensus Constraint-Based Bundle Algorithm (MACCBBA) for observation task allocation in Sensor Web mission concepts for Earth Observation. This algorithm allows for the decentralized allocation of observation tasks amongst a network of Satellites and UAVs based on recently measured data processed on board, or on messages received from other sensors or from the ground. This algorithm is also capable of reaching a feasible plan in a dynamic communications network such as the ones present in some Sensor Web mission concepts and allows for complex temporal constraints and dependencies between tasks to model the value of near-simultaneous co-observations by complementary or synergistic sensors.

Modern autonomous systems are purposed for many challenging scenarios, where agents will face unexpected events and complicated tasks. The presence of disturbance noise with control command and unknown inputs can negatively impact robot performance. Previous research of joint input and state estimation separately studied the continuous and discrete cases without any prior information. This paper combines the continuous and discrete input cases into a unified theory based on the Expectation-Maximum (EM) algorithm. By introducing prior knowledge of events as the constraint, inequality optimization problems are formulated to determine a gain matrix or dynamic weights to realize an optimal input estimation with lower variance and more accurate decision-making. Finally, statistical results from experiments show that our algorithm owns 81% improvement of the variance than KF and 47% improvement than RKF in continuous space; a remarkable improvement of right decision-making probability of our input estimator in discrete space, identification ability is also analyzed by experiments.