Options, the temporally extended courses of actions that can be taken at varying time scale, have provided a concrete, key framework for learning levels of temporal abstraction in hierarchical tasks. While methods of learning options end-to-end is well researched, how to explore good options and actions simultaneously is still challenging. We address this issue by maximizing reward augmented with entropies of both option and action selection policy in options learning. To this end, we reveal our novel optimization objective by reformulating options learning from perspective of probabilistic inference and propose a soft options iteration method to guarantee convergence to the optimum. In implementation, we propose an off-policy algorithm called the maximum-entropy options critic (MEOC) and evaluate it on series of continuous control benchmarks. Comparative results demonstrate that our method outperforms baselines in efficiency and final result on most benchmarks, and the performance exhibits superiority and robustness especially on complex tasks. Ablated studies further explain that entropy maximization on hierarchical exploration promotes learning performance through efficient options specialization and multimodality in action level.

In this article, a multilayered and distributed architecture for mission-oriented miniature fixed-wing UAV swarms is presented. Based on the concept of modularity, the proposed architecture divides the overall system into five layers: 1) low-level control layer; 2) high-level control layer; 3) coordination layer; 4) communication layer; and 5) human interaction layer, and many modules that can be viewed as black boxes with interfaces of inputs and outputs. In this way, not only the complexity of developing a large system can be reduced but also the versatility of supporting diversified missions can be ensured. Furthermore, the proposed architecture is fully distributed that each UAV performs the decision-making procedure autonomously so as to achieve better scalability. Moreover, different kinds of aerial platforms can be feasibly extended by using the control allocation matrices and the integrated hardware box. A prototype swarm system based on the proposed architecture is built and the proposed architecture is evaluated through field experiments with a scale of 21 fixed-wing UAVs. Particularly, to the best of our knowledge, this article is the first work which successfully demonstrates formation flight, target recognition, and tracking missions within an integrated architecture for fixed-wing UAV swarms through field experiments.

This paper presents a novel method-continuous-time Markov decision process (CTMDP)-to address the uncertainties in pursuit-evasion problem. The primary difference between the CTMDP and the Markov decision process (MDP) is that the former takes into account the influence of the transition time between the states. The policy iteration method-based potential performance for solving the CTMDP and its convergence are also presented. The results obtained by MDP-based method demonstrate that it is a special case of CTMDP-based method involving the identity transition rate matrix. To compare the methods, a well-known pursuit-evasion problem, involving two identical cars, is solved as a benchmark. The CTMDP-based method can provide a discretization solution that is close to the analytical solution obtained by the differential game method. Besides, it shows strong robustness against changes in the transition probability, as compared with the traditional MDP-based method. To the best of our knowledge, this is the first attempt to validate the influence of the transition time between the states in such a pursuit-evasion scenario, or in a similar application, solved by an MDP-related model. The CTMDP-based method offers a new approach to solving the pursuit-evasion problem and can be extended to similar optimization applications.