Unmanned Aerial Vehicles (UAVs) are increasingly used as aerial base stations to provide ad hoc communications infrastructure. Building upon prior research efforts which consider either static nodes, 2D trajectories or single UAV systems, this paper focuses on the use of multiple UAVs for providing wireless communication to mobile users in the absence of terrestrial communications infrastructure. In particular, we jointly optimize UAV 3D trajectory and NOMA power allocation to maximize system throughput. Firstly, a weighted K-means-based clustering algorithm establishes UAV-user associations at regular intervals. The efficacy of training a novel Shared Deep Q-Network (SDQN) with action masking is then explored. Unlike training each UAV separately using DQN, the SDQN reduces training time by using the experiences of multiple UAVs instead of a single agent. We also show that SDQN can be used to train a multi-agent system with differing action spaces. Simulation results confirm that: 1) training a shared DQN outperforms a conventional DQN in terms of maximum system throughput (+20%) and training time (-10%); 2) it can converge for agents with different action spaces, yielding a 9% increase in throughput compared to mutual learning algorithms; and 3) combining NOMA with an SDQN architecture enables the network to achieve a better sum rate compared with existing baseline schemes.
相關內容
Unmanned aerial vehicle (UAV)-enabled integrated sensing and communication (ISAC) has attracted growing research interests in the context of sixth-generation (6G) wireless networks, in which UAVs will be exploited as aerial wireless platforms to provide better coverage and enhanced sensing and communication (S&C) services. However, due to the UAVs' size, weight, and power (SWAP) constraints, controllable mobility, and line-of-sight (LoS) air-ground channels, UAV-enabled ISAC introduces both new opportunities and challenges. This article provides an overview of UAV-enabled ISAC, and proposes various solutions for optimizing the S&C performance. In particular, we first introduce UAV-enabled joint S&C, and discuss UAV motion control, wireless resource allocation, and interference management for the cases of single and multiple UAVs. Then, we present two application scenarios for exploiting the synergy between S&C, namely sensing-assisted UAV communication and communication-assisted UAV sensing. Finally, we highlight several interesting research directions to guide and motivate future work.
We propose MIMOC: Motion Imitation from Model-Based Optimal Control. MIMOC is a Reinforcement Learning (RL) controller that learns agile locomotion by imitating reference trajectories from model-based optimal control. MIMOC mitigates challenges faced by other motion imitation RL approaches because the references are dynamically consistent, require no motion retargeting, and include torque references. Hence, MIMOC does not require fine-tuning. MIMOC is also less sensitive to modeling and state estimation inaccuracies than model-based controllers. We validate MIMOC on the Mini-Cheetah in outdoor environments over a wide variety of challenging terrain, and on the MIT Humanoid in simulation. We show cases where MIMOC outperforms model-based optimal controllers, and show that imitating torque references improves the policy's performance.
Finite-time Lyapunov exponents (FTLEs) provide a powerful approach to compute time-varying analogs of invariant manifolds in unsteady fluid flow fields. These manifolds are useful to visualize the transport mechanisms of passive tracers advecting with the flow. However, many vehicles and mobile sensors are not passive, but are instead actuated according to some intelligent trajectory planning or control law; for example, model predictive control and reinforcement learning are often used to design energy-efficient trajectories in a dynamically changing background flow. In this work, we investigate the use of FTLE on such controlled agents to gain insight into optimal transport routes for navigation in known unsteady flows. We find that these controlled FTLE (cFTLE) coherent structures separate the flow field into different regions with similar costs of transport to the goal location. These separatrices are functions of the planning algorithm's hyper-parameters, such as the optimization time horizon and the cost of actuation. Computing the invariant sets and manifolds of active agent dynamics in dynamic flow fields is useful in the context of robust motion control, hyperparameter tuning, and determining safe and collision-free trajectories for autonomous systems. Moreover, these cFTLE structures provide insight into effective deployment locations for mobile agents with actuation and energy constraints to traverse the ocean or atmosphere.
The discovery of individual objectives in collective behavior of complex dynamical systems such as fish schools and bacteria colonies is a long-standing challenge. Inverse reinforcement learning is a potent approach for addressing this challenge but its applicability to dynamical systems, involving continuous state-action spaces and multiple interacting agents, has been limited. In this study, we tackle this challenge by introducing an off-policy inverse multi-agent reinforcement learning algorithm (IMARL). Our approach combines the ReF-ER techniques with guided cost learning. By leveraging demonstrations, our algorithm automatically uncovers the reward function and learns an effective policy for the agents. Through extensive experimentation, we demonstrate that the proposed policy captures the behavior observed in the provided data, and achieves promising results across problem domains including single agent models in the OpenAI gym and multi-agent models of schooling behavior. The present study shows that the proposed IMARL algorithm is a significant step towards understanding collective dynamics from the perspective of its constituents, and showcases its value as a tool for studying complex physical systems exhibiting collective behaviour.
Multicast communication technology is widely applied in wireless environments with a high device density. Traditional wireless network architectures have difficulty flexibly obtaining and maintaining global network state information and cannot quickly respond to network state changes, thus affecting the throughput, delay, and other QoS requirements of existing multicasting solutions. Therefore, this paper proposes a new multicast routing method based on multiagent deep reinforcement learning (MADRL-MR) in a software-defined wireless networking (SDWN) environment. First, SDWN technology is adopted to flexibly configure the network and obtain network state information in the form of traffic matrices representing global network links information, such as link bandwidth, delay, and packet loss rate. Second, the multicast routing problem is divided into multiple subproblems, which are solved through multiagent cooperation. To enable each agent to accurately understand the current network state and the status of multicast tree construction, the state space of each agent is designed based on the traffic and multicast tree status matrices, and the set of AP nodes in the network is used as the action space. A novel single-hop action strategy is designed, along with a reward function based on the four states that may occur during tree construction: progress, invalid, loop, and termination. Finally, a decentralized training approach is combined with transfer learning to enable each agent to quickly adapt to dynamic network changes and accelerate convergence. Simulation experiments show that MADRL-MR outperforms existing algorithms in terms of throughput, delay, packet loss rate, etc., and can establish more intelligent multicast routes.
The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group develops novel machine learning algorithms for autonomous systems control, with a specific focus on deep reinforcement learning and multi-agent reinforcement learning. Research problems include scalable learning of coordinated agent policies and inter-agent communication; reasoning about the behaviours, goals, and composition of other agents from limited observations; and sample-efficient learning based on intrinsic motivation, curriculum learning, causal inference, and representation learning. This article provides a broad overview of the ongoing research portfolio of the group and discusses open problems for future directions.
We introduce DeepNash, an autonomous agent capable of learning to play the imperfect information game Stratego from scratch, up to a human expert level. Stratego is one of the few iconic board games that Artificial Intelligence (AI) has not yet mastered. This popular game has an enormous game tree on the order of $10^{535}$ nodes, i.e., $10^{175}$ times larger than that of Go. It has the additional complexity of requiring decision-making under imperfect information, similar to Texas hold'em poker, which has a significantly smaller game tree (on the order of $10^{164}$ nodes). Decisions in Stratego are made over a large number of discrete actions with no obvious link between action and outcome. Episodes are long, with often hundreds of moves before a player wins, and situations in Stratego can not easily be broken down into manageably-sized sub-problems as in poker. For these reasons, Stratego has been a grand challenge for the field of AI for decades, and existing AI methods barely reach an amateur level of play. DeepNash uses a game-theoretic, model-free deep reinforcement learning method, without search, that learns to master Stratego via self-play. The Regularised Nash Dynamics (R-NaD) algorithm, a key component of DeepNash, converges to an approximate Nash equilibrium, instead of 'cycling' around it, by directly modifying the underlying multi-agent learning dynamics. DeepNash beats existing state-of-the-art AI methods in Stratego and achieved a yearly (2022) and all-time top-3 rank on the Gravon games platform, competing with human expert players.
Effective multi-robot teams require the ability to move to goals in complex environments in order to address real-world applications such as search and rescue. Multi-robot teams should be able to operate in a completely decentralized manner, with individual robot team members being capable of acting without explicit communication between neighbors. In this paper, we propose a novel game theoretic model that enables decentralized and communication-free navigation to a goal position. Robots each play their own distributed game by estimating the behavior of their local teammates in order to identify behaviors that move them in the direction of the goal, while also avoiding obstacles and maintaining team cohesion without collisions. We prove theoretically that generated actions approach a Nash equilibrium, which also corresponds to an optimal strategy identified for each robot. We show through extensive simulations that our approach enables decentralized and communication-free navigation by a multi-robot system to a goal position, and is able to avoid obstacles and collisions, maintain connectivity, and respond robustly to sensor noise.
This paper aims to mitigate straggler effects in synchronous distributed learning for multi-agent reinforcement learning (MARL) problems. Stragglers arise frequently in a distributed learning system, due to the existence of various system disturbances such as slow-downs or failures of compute nodes and communication bottlenecks. To resolve this issue, we propose a coded distributed learning framework, which speeds up the training of MARL algorithms in the presence of stragglers, while maintaining the same accuracy as the centralized approach. As an illustration, a coded distributed version of the multi-agent deep deterministic policy gradient(MADDPG) algorithm is developed and evaluated. Different coding schemes, including maximum distance separable (MDS)code, random sparse code, replication-based code, and regular low density parity check (LDPC) code are also investigated. Simulations in several multi-robot problems demonstrate the promising performance of the proposed framework.
Recently, deep multiagent reinforcement learning (MARL) has become a highly active research area as many real-world problems can be inherently viewed as multiagent systems. A particularly interesting and widely applicable class of problems is the partially observable cooperative multiagent setting, in which a team of agents learns to coordinate their behaviors conditioning on their private observations and commonly shared global reward signals. One natural solution is to resort to the centralized training and decentralized execution paradigm. During centralized training, one key challenge is the multiagent credit assignment: how to allocate the global rewards for individual agent policies for better coordination towards maximizing system-level's benefits. In this paper, we propose a new method called Q-value Path Decomposition (QPD) to decompose the system's global Q-values into individual agents' Q-values. Unlike previous works which restrict the representation relation of the individual Q-values and the global one, we leverage the integrated gradient attribution technique into deep MARL to directly decompose global Q-values along trajectory paths to assign credits for agents. We evaluate QPD on the challenging StarCraft II micromanagement tasks and show that QPD achieves the state-of-the-art performance in both homogeneous and heterogeneous multiagent scenarios compared with existing cooperative MARL algorithms.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191