Reasoning about uncertainty is vital in many real-life autonomous systems. However, current state-of-the-art planning algorithms cannot either reason about uncertainty explicitly, or do so with a high computational burden. Here, we focus on making informed decisions efficiently, using reward functions that explicitly deal with uncertainty. We formulate an approximation, namely an abstract observation model, that uses an aggregation scheme to alleviate computational costs. We derive bounds on the expected information-theoretic reward function and, as a consequence, on the value function. We then propose a method to refine aggregation to achieve identical action selection with a fraction of the computational time.

How can we plan efficiently in a large and complex environment when the time budget is limited? However, there are three main limitations of this "twophase" Given the original simulator of the environment, paradigm, where a simulator is learned offline and which may be computationally very demanding, we then used as-is for online simulation and planning. First, no propose to learn online an approximate but much planning is possible until the offline learning phase finishes, faster simulator that improves over time. To plan which can take a long time. Second, the separation of learning reliably and efficiently while the approximate simulator and planning raises a question on what data collection policy is learning, we develop a method that adaptively should be used during training to ensure good online prediction decides which simulator to use for every simulation, during planning. We empirically demonstrate that when based on a statistic that measures the accuracy the training data is collected by a uniform random policy, the of the approximate simulator. This allows us to learned influence predictors can perform poorly during online use the approximate simulator to replace the original planning, due to distribution shift. Third, completely replacing simulator for faster simulations when it is accurate the original simulator with the approximate one after enough under the current context, thus trading training implies a risk of poor planning performance in certain off simulation speed and accuracy. Experimental situations, which is hard to detect in advance.

Path planning obtains the trajectory from one point to another with the robot’s kinematics model and environment understanding. However, as the localization uncertaining through the odometry sensors is inevitably affected, the position of the moving path will deviate further and further compared to the original path, which leads to path drift in GPS denied environments. This paper proposes a novel path planning algorithm based on Dijkstra to address such issues. By combining statistical characteristics of localization error caused by dead-reckoning, the replanned path with minimum cumulative error is generated with uniforming distribution in the searching space. The simulation verifies the effectiveness of the proposed algorithm. Compared with the path generated by traditional planning algorithm, the result of the proposed algorithm has achieved an effective reduction in cumulative errors. Even if the accuracy of the odometry sensor is quite low, our method can still effectively eliminate the cumulative error during the planning process.

In the digital economy, data is the new gold– indeed, there's a new gold rush -- for businesses. To obtain value from gold, the raw material first needs to be processed -- minted into coins or fashioned into jewelry and other products that consumers desire to own and purchase. Similarly, data needs to be processed -- manipulated and analyzed -- to extract real business value. And this is where data science comes in. Data scientists are the prospectors and the tools they use are the innovations that make them more effective.

Digital Transformation moved at a relatively slow pace for the past ten years, mainly focusing on improving products, employee experience and processes. But then, after COVID – 19 hit, IT decision-makers were forced to prioritize their IT initiatives in order to increase digital investments. According to IDC, over the next four years, worldwide Digital Transformation technology investment is set to reach at least $7.4 trillion and will be the first time that DX will account for the majority of IT spending – predicted to be a huge 53% of budgets. Digital transformation is a set of methodologies and tools which are used by modern companies to optimize their operational activities, such as increasing their reach power, providing differentiated service and increasing performance. However, digital transformation is not just a new department in the firm, but it is definitely a game-changer in technology's role in the corporate environment. That's why it is increasingly being seen as the 4th Industrial Revolution. "Think of digital transformation less as a technology project to be finished than as a state of perpetual agility, always ready to evolve for whatever customers want next, and you'll be pointed down the right path."-

Intelligent physical systems as embodied cognitive systems must perform high-level reasoning while concurrently managing an underlying control architecture. The link between cognition and control must manage the problem of converting continuous values from the real world to symbolic representations (and back). To generate effective behaviors, reasoning must include a capacity to replan, acquire and update new information, detect and respond to anomalies, and perform various operations on system goals. But, these processes are not independent and need further exploration. This paper examines an agent's choices when multiple goal operations co-occur and interact, and it establishes a method of choosing between them. We demonstrate the benefits and discuss the trade offs involved with this and show positive results in a dynamic marine search task.

Significant hurdles leaders face this year include managing talent, formulating strategies, operational plans, and organizing employee tasks in ways that ensure everyone accesses growth opportunities. These challenges emphasize the importance of good strategy, and are essential for organizational survival. Vijay Pereira, Professor and head of department of people and organizations, at NEOMA Business School in France, believes artificial intelligence (AI) can help leaders undertake these challenges. For example, his recent work concludes that evolutionary computation and data mining can explore large databases or social media to locate potential talented individuals for recruitment purposes. In addition, machine learning helps reanalyze and recognize patterns from data collected from existing decision support systems to help organizations improve their strategic planning processes.

Major international airlines rushed on Tuesday to rejig or cancel flights to the United States on the eve of a 5G wireless rollout that triggered safety concerns, despite two wireless carriers saying they will delay parts of the deployment. The Federal Aviation Administration has warned that potential 5G interference could affect height readings that play a key role in bad-weather landings on some jets and airlines say the Boeing 777 is among models initially in the spotlight. Despite an announcement by AT&T and Verizon that they would delay turning on some 5G towers near airports, several airlines still canceled flights. Others said more cancellations were likely unless the FAA issued new formal guidance in the wake of the wireless announcements. The world's largest operator of the Boeing 777, Dubai's Emirates, said it would suspend flights to nine U.S. destinations from Jan. 19, the planned date for the deployment of 5G wireless services.

How resources are deployed to secure critical targets in networks can be modelled by Network Security Games (NSGs). While recent advances in deep learning (DL) provide a powerful approach to dealing with large-scale NSGs, DL methods such as NSG-NFSP suffer from the problem of data inefficiency. Furthermore, due to centralized control, they cannot scale to scenarios with a large number of resources. In this paper, we propose a novel DL-based method, NSGZero, to learn a non-exploitable policy in NSGs. NSGZero improves data efficiency by performing planning with neural Monte Carlo Tree Search (MCTS). Our main contributions are threefold. First, we design deep neural networks (DNNs) to perform neural MCTS in NSGs. Second, we enable neural MCTS with decentralized control, making NSGZero applicable to NSGs with many resources. Third, we provide an efficient learning paradigm, to achieve joint training of the DNNs in NSGZero. Compared to state-of-the-art algorithms, our method achieves significantly better data efficiency and scalability.

Opponent modeling is the ability to use prior knowledge and observations in order to predict the behavior of an opponent. This survey presents a comprehensive overview of existing opponent modeling techniques for adversarial domains, many of which must address stochastic, continuous, or concurrent actions, and sparse, partially observable payoff structures. We discuss all the components of opponent modeling systems, including feature extraction, learning algorithms, and strategy abstractions. These discussions lead us to propose a new form of analysis for describing and predicting the evolution of game states over time. We then introduce a new framework that facilitates method comparison, analyze a representative selection of techniques using the proposed framework, and highlight common trends among recently proposed methods. Finally, we list several open problems and discuss future research directions inspired by AI research on opponent modeling and related research in other disciplines.