Behaviors of the synthetic characters in current military simulations are limited since they are generally generated by rule-based and reactive computational models with minimal intelligence. Such computational models cannot adapt to reflect the experience of the characters, resulting in brittle intelligence for even the most effective behavior models devised via costly and labor-intensive processes. Observation-based behavior model adaptation that leverages machine learning and the experience of synthetic entities in combination with appropriate prior knowledge can address the issues in the existing computational behavior models to create a better training experience in military training simulations. In this paper, we introduce a framework that aims to create autonomous synthetic characters that can perform coherent sequences of believable behavior while being aware of human trainees and their needs within a training simulation. This framework brings together three mutually complementary components. The first component is a Unity-based simulation environment - Rapid Integration and Development Environment (RIDE) - supporting One World Terrain (OWT) models and capable of running and supporting machine learning experiments. The second is Shiva, a novel multi-agent reinforcement and imitation learning framework that can interface with a variety of simulation environments, and that can additionally utilize a variety of learning algorithms. The final component is the Sigma Cognitive Architecture that will augment the behavior models with symbolic and probabilistic reasoning capabilities. We have successfully created proof-of-concept behavior models leveraging this framework on realistic terrain as an essential step towards bringing machine learning into military simulations.

Meta-reinforcement learning (RL) addresses the problem of sample inefficiency in deep RL by using experience obtained in past tasks for a new task to be solved. However, most meta-RL methods require partially or fully on-policy data, i.e., they cannot reuse the data collected by past policies, which hinders the improvement of sample efficiency. To alleviate this problem, we propose a novel off-policy meta-RL method, embedding learning and evaluation of uncertainty (ELUE). An ELUE agent is characterized by the learning of a feature embedding space shared among tasks. It learns a belief model over the embedding space and a belief-conditional policy and Q-function. Then, for a new task, it collects data by the pretrained policy, and updates its belief based on the belief model. Thanks to the belief update, the performance can be improved with a small amount of data. In addition, it updates the parameters of the neural networks to adjust the pretrained relationships when there are enough data. We demonstrate that ELUE outperforms state-of-the-art meta RL methods through experiments on meta-RL benchmarks.

As an emerging technique, mobile edge computing (MEC) introduces a new processing scheme for various distributed communication-computing systems such as industrial Internet of Things (IoT), vehicular communication, smart city, etc. In this work, we mainly focus on the timeliness of the MEC systems where the freshness of the data and computation tasks is significant. Firstly, we formulate a kind of age-sensitive MEC models and define the average age of information (AoI) minimization problems of interests. Then, a novel policy based multi-agent deep reinforcement learning (RL) framework, called heterogeneous multi-agent actor critic (H-MAAC), is proposed as a paradigm for joint collaboration in the investigated MEC systems, where edge devices and center controller learn the interactive strategies through their own observations. To improves the system performance, we develop the corresponding online algorithm by introducing an edge federated learning mode into the multi-agent cooperation whose advantages on learning convergence can be guaranteed theoretically. To the best of our knowledge, it's the first joint MEC collaboration algorithm that combines the edge federated mode with the multi-agent actor-critic reinforcement learning. Furthermore, we evaluate the proposed approach and compare it with classical RL based methods. As a result, the proposed framework not only outperforms the baseline on average system age, but also promotes the stability of training process. Besides, the simulation results provide some innovative perspectives for the system design under the edge federated collaboration.

We study reinforcement learning (RL) with linear function approximation under the adaptivity constraint. We consider two popular limited adaptivity models: batch learning model and rare policy switch model, and propose two efficient online RL algorithms for linear Markov decision processes. In specific, for the batch learning model, our proposed LSVI-UCB-Batch algorithm achieves an $\tilde O(\sqrt{d^3H^3T} + dHT/B)$ regret, where $d$ is the dimension of the feature mapping, $H$ is the episode length, $T$ is the number of interactions and $B$ is the number of batches. Our result suggests that it suffices to use only $\sqrt{T/dH}$ batches to obtain $\tilde O(\sqrt{d^3H^3T})$ regret. For the rare policy switch model, our proposed LSVI-UCB-RareSwitch algorithm enjoys an $\tilde O(\sqrt{d^3H^3T[1+T/(dH)]^{dH/B}})$ regret, which implies that $dH\log T$ policy switches suffice to obtain the $\tilde O(\sqrt{d^3H^3T})$ regret. Our algorithms achieve the same regret as the LSVI-UCB algorithm (Jin et al., 2019), yet with a substantially smaller amount of adaptivity.

The purpose of accounting audit is to have clear understanding on the financial activities of a company, which can be enhanced by machine learning or reinforcement learning as numeric analysis better than manual analysis can be made. For the purpose of assessment on the relevance, completeness and accuracy of the information produced by entity pertaining to the newly implemented International Financial Reporting Standard 16 Lease (IFRS 16) is one of such candidates as its characteristic of requiring the understanding on the nature of contracts and its complete analysis from listing up without omission, which can be enhanced by the digitalization of contracts for the purpose of creating the lists, still leaving the need of auditing cash flows of companies for the possible omission due to the potential error at the stage of data collection, especially for entities with various short or middle term business sites and related leases, such as construction entities. The implementation of the reinforcement learning and its well-known code is to be made for the purpose of drawing the possibility and utilizability of interpreters from domain knowledge to numerical system, also can be called 'gamification interpreter' or 'numericalization interpreter' which can be referred or compared to the extrapolation with nondimensional numbers, such as Froude Number, in physics, which was a source of inspiration at this study. Studies on the interpreters can be able to empower the utilizability of artificial general intelligence in domain and commercial area.

Entity alignment (EA) is the task of identifying the entities that refer to the same real-world object but are located in different knowledge graphs (KGs). For entities to be aligned, existing EA solutions treat them separately and generate alignment results as ranked lists of entities on the other side. Nevertheless, this decision-making paradigm fails to take into account the interdependence among entities. Although some recent efforts mitigate this issue by imposing the 1-to-1 constraint on the alignment process, they still cannot adequately model the underlying interdependence and the results tend to be sub-optimal. To fill in this gap, in this work, we delve into the dynamics of the decision-making process, and offer a reinforcement learning (RL) based model to align entities collectively. Under the RL framework, we devise the coherence and exclusiveness constraints to characterize the interdependence and restrict collective alignment. Additionally, to generate more precise inputs to the RL framework, we employ representative features to capture different aspects of the similarity between entities in heterogeneous KGs, which are integrated by an adaptive feature fusion strategy. Our proposal is evaluated on both cross-lingual and mono-lingual EA benchmarks and compared against state-of-the-art solutions. The empirical results verify its effectiveness and superiority.

The goal of traffic signal control is to coordinate multiple traffic signals to improve the traffic efficiency of a district or a city. In this work, we propose a novel Meta Variationally Intrinsic Motivated (MetaVIM) RL method, and aim to learn the decentralized polices of each traffic signal only conditioned on its local observation. MetaVIM makes three novel contributions. Firstly, to make the model available to new unseen target scenarios, we formulate the traffic signal control as a meta-learning problem over a set of related tasks. The train scenario is divided as multiple partially observable Markov decision process (POMDP) tasks, and each task corresponds to a traffic light. In each task, the neighbours are regarded as an unobserved part of the state. Secondly, we assume that the reward, transition and policy functions vary across different tasks but share a common structure, and a learned latent variable conditioned on the past trajectories is proposed for each task to represent the specific information of the current task in these functions, then is further brought into policy for automatically trade off between exploration and exploitation to induce the RL agent to choose the reasonable action. In addition, to make the policy learning stable, four decoders are introduced to predict the received observations and rewards of the current agent with/without neighbour agents' policies, and a novel intrinsic reward is designed to encourage the received observation and reward invariant to the neighbour agents. Empirically, extensive experiments conducted on CityFlow demonstrate that the proposed method substantially outperforms existing methods and shows superior generalizability.

Direct policy search serves as one of the workhorses in modern reinforcement learning (RL), and its applications in continuous control tasks have recently attracted increasing attention. In this work, we investigate the convergence theory of policy gradient (PG) methods for learning the linear risk-sensitive and robust controller. In particular, we develop PG methods that can be implemented in a derivative-free fashion by sampling system trajectories, and establish both global convergence and sample complexity results in the solutions of two fundamental settings in risk-sensitive and robust control: the finite-horizon linear exponential quadratic Gaussian, and the finite-horizon linear-quadratic disturbance attenuation problems. As a by-product, our results also provide the first sample complexity for the global convergence of PG methods on solving zero-sum linear-quadratic dynamic games, a nonconvex-nonconcave minimax optimization problem that serves as a baseline setting in multi-agent reinforcement learning (MARL) with continuous spaces. One feature of our algorithms is that during the learning phase, a certain level of robustness/risk-sensitivity of the controller is preserved, which we termed as the implicit regularization property, and is an essential requirement in safety-critical control systems.

Aiming at the traditional grasping method for manipulators based on 2D camera, when faced with the scene of gathering or covering, it can hardly perform well in unstructured scenes that appear as gathering and covering, for the reason that can't recognize objects accurately in cluster scenes from a single perspective and the manipulators can't make the environment better for grasping. In this case, a novel method of pushing-grasping collaborative based on the deep Q-network in dual perspectives is proposed in this paper. This method adopts an improved deep Q network algorithm, with an RGB-D camera to obtain the information of objects' RGB images and point clouds from two perspectives, and combines the pushing and grasping actions so that the trained manipulator can make the scenes better for grasping so that it can perform well in more complicated grasping scenes. What's more, we improved the reward function of the deep Q-network and propose the piecewise reward function to speed up the convergence of the deep Q-network. We trained different models and tried different methods in the V-REP simulation environment, and it concluded that the method proposed in this paper converges quickly and the success rate of grasping objects in unstructured scenes raises up to 83.5%. Besides, it shows the generalization ability and well performance when novel objects appear in the scenes that the manipulator has never grasped before.

Sensors are being extensively deployed and are expected to expand at significant rates in the coming years. They typically generate a large volume of data on the internet of things (IoT) application areas like smart cities, intelligent traffic systems, smart grid, and e-health. Cloud, edge and fog computing are potential and competitive strategies for collecting, processing, and distributing IoT data. However, cloud, edge, and fog-based solutions need to tackle the distribution of a high volume of IoT data efficiently through constrained and limited resource network infrastructures. This paper addresses the issue of conveying a massive volume of IoT data through a network with limited communications resources (bandwidth) using a cognitive communications resource allocation based on Reinforcement Learning (RL) with SARSA algorithm. The proposed network infrastructure (PSIoTRL) uses a Publish/ Subscribe architecture to access massive and highly distributed IoT data. It is demonstrated that the PSIoTRL bandwidth allocation for buffer flushing based on SARSA enhances the IoT aggregator buffer occupation and network link utilization.