Real-Time Online Goal Recognition in Continuous Domains via Deep Reinforcement Learning.

The problem of goal recognition involves inferring the high-level task goals of an agent based on observations of its behavior in an environment. Current methods for achieving this task rely on offline comparison inference of observed behavior in discrete environments, which presents several challenges. First, accurately modeling the behavior of the observed agent requires significant computational resources. Second, continuous simulation environments cannot be accurately recognized using existing methods. Finally, real-time computing power is required to infer the likelihood of each potential goal. In this paper, we propose an advanced and efficient real-time online goal recognition algorithm based on deep reinforcement learning in continuous domains. By leveraging the offline modeling of the observed agent's behavior with deep reinforcement learning, our algorithm achieves real-time goal recognition. We evaluate the algorithm's online goal recognition accuracy and stability in continuous simulation environments under communication constraints.

Single Real Goal, Magnitude-Based Deceptive Path-Planning.

Deceptive path-planning is the task of finding a path so as to minimize the probability of an observer (or a defender) identifying the observed agent's final goal before the goal has been reached. It is one of the important approaches to solving real-world challenges, such as public security, strategic transportation, and logistics. Existing methods either cannot make full use of the entire environments' information, or lack enough flexibility for balancing the path's deceptivity and available moving resource. In this work, building on recent developments in probabilistic goal recognition, we formalized a single real goal magnitude-based deceptive path-planning problem followed by a mixed-integer programming based deceptive path maximization and generation method. The model helps to establish a computable foundation for any further imposition of different deception concepts or strategies, and broadens its applicability in many scenarios. Experimental results showed the effectiveness of our methods in deceptive path-planning compared to the existing one.

Improving the Scalability of the Magnitude-Based Deceptive Path-Planning Using Subgoal Graphs.

Deceptive path-planning is the task of finding a path so as to minimize the probability of an observer (or a defender) identifying the observed agent's final goal before the goal has been reached. Magnitude-based deceptive path-planning takes advantage of the quantified deceptive values upon each grid or position to generate paths that are deceptive. Existing methods using optimization techniques cannot satisfy the time constraints when facing with the large-scale terrain, as its computation time grows exponentially with the size of road maps or networks. In this work, building on recent developments in the optimal path planner, the paper proposes a hybrid solution between map scaling and hierarchical abstractions. By leading the path deception information down into a general purpose but highly-efficient path-planning formulation, the paper substantially speeds up the task upon large scale terrains with an admissible loss of deception.

Dibenzyl sulfoxide.

There are two independent mol-ecules in the asymmetric unit of the title compound, C(14)H(14)OS, which have asymmetric S-C bonds [1.791 (5) and 1.804 (5) Šin one mol-ecule and 1.798 (5) and 1.804 (5) Šin the other]. The long axes of the mol-ecules are directed along the crystallographic b axis.