This work has been submitted to the IEEE for possible publication. Abstract With the development of the 5G and Internet of Things, amounts of wireless devices need to share the limited spectrum resources. Dynamic spectrum access (DSA) is a promising paradigm to remedy the problem of inef!cient spectrum utilization brought upon by the historical command-and-control approach to spectrum allocation. In this paper, we investigate the distributed DSA problem for multiuser in a typical multi-channel cognitive radio network. The problem is formulated as a decentralized partially observable Markov decision process (Dec-POMDP), and we proposed a centralized off-line training and distributed on-line execution framework based on cooperative multi-agent reinforcement learning (MARL). We employ the deep recurrent Q-network (DRQN) to address the partial observability of the state for each cognitive user. The ultimate goal is to learn a cooperative strategy which maximizes the sum throughput of cognitive radio network in distributed fashion without coordination information exchange between cognitive users. This work was supported in part by the National Natural Science Foundation of China under Grant 6193000305. X. Tan, L. Zhou, Y. Sun, H. Wang, H. Zhao and J. Wei are all with College of Electronic Science and Technology, National University of Defense Technology, Changsha, 410073, China (E-mail: {tanxiang, zhouli2035, haijunwang14, sunyuli19, haitaozhao, wjbhw}@nudt.edu.cn). Boon-Chong Seet is with the Department of Electrical and Electronic Engineering, Auckland University of Technology, Auckland 1142, New Zealand (E-mail: boon-chong.seet@aut.ac.nz). Victor C. M. Leung is with Shenzhen University, Shenzhen, China and the University of British Columbia, Vancouver, Canada (E-mail: vleung@ieee.org). 2 From the simulation results, we can observe that the proposed algorithm can converge fast and achieve almost the optimal performance. The future network is involving into the Internet of Everything.

In many real-world imitation learning tasks, the demonstrator and the learner have to act in different but full observation spaces. This situation generates significant obstacles for existing imitation learning approaches to work, even when they are combined with traditional space adaptation techniques. The main challenge lies in bridging expert's occupancy measures to learner's dynamically changing occupancy measures under the different observation spaces. In this work, we model the above learning problem as Heterogeneous Observations Imitation Learning (HOIL). We propose the Importance Weighting with REjection (IWRE) algorithm based on the techniques of importance-weighting, learning with rejection, and active querying to solve the key challenge of occupancy measure matching. Experimental results show that IWRE can successfully solve HOIL tasks, including the challenging task of transforming the vision-based demonstrations to random access memory (RAM)-based policies under the Atari domain.

What is the future of chatbots? As the Chief Product Officer of an AI bot-building platform, I get this question a lot, and there are many ways to answer it. As a company, I think we can only answer this question if we know where we are planning to go. Which goal are we aiming for? Chatlayer's mission is to make it possible for everyone to have a personal conversation at any time.

"A period that had been broadly described as engagement has come to an end," Kurt Campbell, the Indo-Pacific Coordinator at the United States (US) National Security Council, told a virtual audience in May on the subject of US-China relations. "The dominant paradigm is going to be competition." On several occasions, Campbell has highlighted that one of the major arenas of this competition will concern technology. This is increasingly reflected in US national security structures. Today, there is both a senior director and coordinator for technology and national security at the White House; the National Economic Council has briefed the Cabinet on supply chain resilience; and the focus of Department of Defense policy reviews have been on emerging military technologies.

The graph represents a network of 4,327 Twitter users whose tweets in the requested range contained "#VR", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Tuesday, 15 June 2021 at 17:45 UTC. The requested start date was Tuesday, 15 June 2021 at 00:01 UTC and the maximum number of days (going backward) was 14. The maximum number of tweets collected was 7,500. The tweets in the network were tweeted over the 2-day, 5-hour, 6-minute period from Saturday, 12 June 2021 at 16:46 UTC to Monday, 14 June 2021 at 21:52 UTC.

Microsoft's sleek and stylish Surface Laptop is back for its fourth generation with faster performance and a greater variety of chips. The Surface Laptop 4 is available with either a 13.5in or a 15in screen and starts at £999 in the UK, $999 in the US or $1,599 in Australia sitting above the Surface Laptop Go as Microsoft's mainstream premium notebook, competing with the similarly priced Dell XPS 13 and Apple MacBook Air, among others. Very little has changed on the outside, matching the dimensions, weight, port selection and design of 2020's Surface Laptop 3. Here tested with a 13.5in screen, it still looks and feels sleek with its aluminium lid, choice of Alcantara fabric or aluminium deck and bright and crisp touch screen. The keyboard is excellent while the large trackpad is smooth and precise. The speakers are loud and clear with reasonable bass for a laptop, while the 720p webcam and microphones are better than most for video calls.

Detecting and responding to novel situations in open-world environments is a key capability of human cognition. Current artificial intelligence (AI) researchers strive to develop systems that can perform in open-world environments. Novelty detection is an important ability of such AI systems. In an open-world, novelties appear in various forms and the difficulty to detect them varies. Therefore, to accurately evaluate the detection capability of AI systems, it is necessary to investigate the difficulty to detect novelties. In this paper, we propose a qualitative physics-based method to quantify the difficulty of novelty detection focusing on open-world physical domains. We apply our method in a popular physics simulation game, Angry Birds. We conduct an experiment with human players with different novelties in Angry Birds to validate our method. Results indicate that the calculated difficulty values are in line with the detection difficulty of the human players.

This paper proposes methods for unsupervised lexical acquisition for relative spatial concepts using spoken user utterances. A robot with a flexible spoken dialog system must be able to acquire linguistic representation and its meaning specific to an environment through interactions with humans as children do. Specifically, relative spatial concepts (e.g., front and right) are widely used in our daily lives, however, it is not obvious which object is a reference object when a robot learns relative spatial concepts. Therefore, we propose methods by which a robot without prior knowledge of words can learn relative spatial concepts. The methods are formulated using a probabilistic model to estimate the proper reference objects and distributions representing concepts simultaneously. The experimental results show that relative spatial concepts and a phoneme sequence representing each concept can be learned under the condition that the robot does not know which located object is the reference object. Additionally, we show that two processes in the proposed method improve the estimation accuracy of the concepts: generating candidate word sequences by class n-gram and selecting word sequences using location information. Furthermore, we show that clues to reference objects improve accuracy even though the number of candidate reference objects increases.

With the surge in the number of hyperparameters and training times of modern machine learning models, hyperparameter tuning is becoming increasingly expensive. Although methods have been proposed to speed up tuning via knowledge transfer, they typically require the final performance of hyperparameters and do not focus on low-fidelity information. Nevertheless, this common practice is suboptimal and can incur an unnecessary use of resources. It is more cost-efficient to instead leverage the low-fidelity tuning observations to measure inter-task similarity and transfer knowledge from existing to new tasks accordingly. However, performing multi-fidelity tuning comes with its own challenges in the transfer setting: the noise in the additional observations and the need for performance forecasting. Therefore, we conduct a thorough analysis of the multi-task multi-fidelity Bayesian optimization framework, which leads to the best instantiation--amortized auto-tuning (AT2). We further present an offline-computed 27-task hyperparameter recommendation (HyperRec) database to serve the community. Extensive experiments on HyperRec and other real-world databases illustrate the effectiveness of our AT2 method.

Multiple attacks have shown that in-vehicle networks have vulnerabilities which can be exploited. Securing the Controller Area Network (CAN) for modern vehicles has become a necessary task for car manufacturers. Some attacks inject potentially large amount of fake messages into the CAN network; however, such attacks are relatively easy to detect. In more sophisticated attacks, the original messages are modified, making the detection a more complex problem. In this paper, we present a novel machine learning based intrusion detection method for CAN networks. We focus on detecting message modification attacks, which do not change the timing patterns of communications. Our proposed temporal convolutional network-based solution can learn the normal behavior of CAN signals and differentiate them from malicious ones. The method is evaluated on multiple CAN-bus message IDs from two public datasets including different types of attacks. Performance results show that our lightweight approach compares favorably to the state-of-the-art unsupervised learning approach, achieving similar or better accuracy for a wide range of scenarios with a significantly lower false positive rate.