Hierarchical Reinforcement Learning for Swarm Confrontation with High Uncertainty

In swarm robotics, confrontation including the pursuit-evasion game is a key scenario. High uncertainty caused by unknown opponents' strategies and dynamic obstacles complicates the action space into a hybrid decision process. Although the deep reinforcement learning method is significant for swarm confrontation since it can handle various sizes, as an end-to-end implementation, it cannot deal with the hybrid process. Here, we propose a novel hierarchical reinforcement learning approach consisting of a target allocation layer, a path planning layer, and the underlying dynamic interaction mechanism between the two layers, which indicates the quantified uncertainty. It decouples the hybrid process into discrete allocation and continuous planning layers, with a probabilistic ensemble model to quantify the uncertainty and regulate the interaction frequency adaptively. Furthermore, to overcome the unstable training process introduced by the two layers, we design an integration training method including pre-training and cross-training, which enhances the training efficiency and stability. Experiment results in both comparison and ablation studies validate the effectiveness and generalization performance of our proposed approach.

Model predictive control-based value estimation for efficient reinforcement learning

Reinforcement learning suffers from limitations in real practices primarily due to the numbers of required interactions with virtual environments. It results in a challenging problem that we are implausible to obtain an optimal strategy only with a few attempts for many learning method. Hereby, we design an improved reinforcement learning method based on model predictive control that models the environment through a data-driven approach. Based on learned environmental model, it performs multi-step prediction to estimate the value function and optimize the policy. The method demonstrates higher learning efficiency, faster convergent speed of strategies tending to the optimal value, and fewer sample capacity space required by experience replay buffers. Experimental results, both in classic databases and in a dynamic obstacle avoidance scenario for unmanned aerial vehicle, validate the proposed approaches.

UAV Pathfinding in Dynamic Obstacle Avoidance with Multi-agent Reinforcement Learning

Multi-agent reinforcement learning based methods are significant for online planning of feasible and safe paths for agents in dynamic and uncertain scenarios. Although some methods like fully centralized and fully decentralized methods achieve a certain measure of success, they also encounter problems such as dimension explosion and poor convergence, respectively. In this paper, we propose a novel centralized training with decentralized execution method based on multi-agent reinforcement learning to solve the dynamic obstacle avoidance problem online. In this approach, each agent communicates only with the central planner or only with its neighbors, respectively, to plan feasible and safe paths online. We improve our methods based on the idea of model predictive control to increase the training efficiency and sample utilization of agents. The experimental results in both simulation, indoor, and outdoor environments validate the effectiveness of our method. The video is available at https://www.bilibili.com/video/BV1gw41197hV/?vd_source=9de61aecdd9fb684e546d032ef7fe7bf

Data-driven, multi-moment fluid modeling of Landau damping

Deriving governing equations of complex physical systems based on first principles can be quite challenging when there are certain unknown terms and hidden physical mechanisms in the systems. In this work, we apply a deep learning architecture to learn fluid partial differential equations (PDEs) of a plasma system based on the data acquired from a fully kinetic model. The learned multi-moment fluid PDEs are demonstrated to incorporate kinetic effects such as Landau damping. Based on the learned fluid closure, the data-driven, multi-moment fluid modeling can well reproduce all the physical quantities derived from the fully kinetic model. The calculated damping rate of Landau damping is consistent with both the fully kinetic simulation and the linear theory. The data-driven fluid modeling of PDEs for complex physical systems may be applied to improve fluid closure and reduce the computational cost of multi-scale modeling of global systems.

An Improved Reinforcement Learning Algorithm for Learning to Branch

Most combinatorial optimization problems can be formulated as mixed integer linear programming (MILP), in which branch-and-bound (B\&B) is a general and widely used method. Recently, learning to branch has become a hot research topic in the intersection of machine learning and combinatorial optimization. In this paper, we propose a novel reinforcement learning-based B\&B algorithm. Similar to offline reinforcement learning, we initially train on the demonstration data to accelerate learning massively. With the improvement of the training effect, the agent starts to interact with the environment with its learned policy gradually. It is critical to improve the performance of the algorithm by determining the mixing ratio between demonstration and self-generated data. Thus, we propose a prioritized storage mechanism to control this ratio automatically. In order to improve the robustness of the training process, a superior network is additionally introduced based on Double DQN, which always serves as a Q-network with competitive performance. We evaluate the performance of the proposed algorithm over three public research benchmarks and compare it against strong baselines, including three classical heuristics and one state-of-the-art imitation learning-based branching algorithm. The results show that the proposed algorithm achieves the best performance among compared algorithms and possesses the potential to improve B\&B algorithm performance continuously.