This study aims to minimize the influence of fake news on social networks by deploying debunkers to propagate true news. This is framed as a reinforcement learning problem, where, at each stage, one user is selected to propagate true news. A challenging issue is episodic reward where the "net" effect of selecting individual debunkers cannot be discerned from the interleaving information propagation on social networks, and only the collective effect from mitigation efforts can be observed. Existing Self-Imitation Learning (SIL) methods have shown promise in learning from episodic rewards, but are ill-suited to the real-world application of fake news mitigation because of their poor sample efficiency. To learn a more effective debunker selection policy for fake news mitigation, this study proposes NAGASIL - Negative sampling and state Augmented Generative Adversarial Self-Imitation Learning, which consists of two improvements geared towards fake news mitigation: learning from negative samples, and an augmented state representation to capture the "real" environment state by integrating the current observed state with the previous state-action pairs from the same campaign. Experiments on two social networks show that NAGASIL yields superior performance to standard GASIL and state-of-the-art fake news mitigation models.

The media had a field day when a Google engineer recently claimed that the company's artificial intelligence technology had become "sentient." For every article joking about Skynet and HAL 9000, there was another assuming it must be true and questioning the ethics of it all. Missing in most of the coverage was any recognition of how far and fast this technology has advanced and how broadly it impacts our lives on a daily basis, in ways both large and small. It was only ten years ago on June 26, 2012 that the New York Times wrote about Google's deep learning discovery using machine learning, essentially teaching a computer to train itself with enormous amounts of data. The article was headlined How Many Computers to Identify a Cat? 16,000.

Organizations are leaning in hard to technologies like AI to facilitate faster, more productive operations. But in a recent meeting with a large company to discuss how AI can improve their customer and support experience, I was reminded there's more to the story than zeros and ones. AI works best when you put people in the center of your efforts. After my presentation, one of their AI experts started peppering me with questions on model recommendations for different situations in the customer support journey. Valid questions, all--but she was missing a crucial part of the conversation: people. I asked her, "What behavior are you trying to change?

Imitation learning is a primary approach to improve the efficiency of reinforcement learning by exploiting the expert demonstrations. However, in many real scenarios, obtaining expert demonstrations could be extremely expensive or even impossible. To overcome this challenge, in this paper, we propose a novel learning framework called Co-Imitation Learning (CoIL) to exploit the past good experiences of the agents themselves without expert demonstration. Specifically, we train two different agents via letting each of them alternately explore the environment and exploit the peer agent's experience. While the experiences could be valuable or misleading, we propose to estimate the potential utility of each piece of experience with the expected gain of the value function. Thus the agents can selectively imitate from each other by emphasizing the more useful experiences while filtering out noisy ones. Experimental results on various tasks show significant superiority of the proposed Co-Imitation Learning framework, validating that the agents can benefit from each other without external supervision.

As you've probably noticed, Machine Learning and Artificial Intelligence are here to stay and will continue to disrupt the market. Many products have inherently integrated AI functions (i.e., Netflix's suggestions, Facebook's auto-tagging, Google's question answering), and by 2024, 69% of the manager's routine workload, will be automated, as Gartner forecasts. A lot of work has been done around designing products that make AI accessible for users, but what about designing a product that improves the AI model? How does UX approach the development of better AI? I've always been very excited about AI, and for the past couple of months, I've been working on the Product Management and UX of several highly technical and advanced AI products. In my experience, bridging the gap between the science behind Machine Learning(ML) and the end-user is a real challenge, but it's crucial and valuable.

Cooperative Multi-agent Reinforcement Learning (MARL) is crucial for cooperative decentralized decision learning in many domains such as search and rescue, drone surveillance, package delivery and fire fighting problems. In these domains, a key challenge is learning with a few good experiences, i.e., positive reinforcements are obtained only in a few situations (e.g., on extinguishing a fire or tracking a crime or delivering a package) and in most other situations there is zero or negative reinforcement. Learning decisions with a few good experiences is extremely challenging in cooperative MARL problems due to three reasons. First, compared to the single agent case, exploration is harder as multiple agents have to be coordinated to receive a good experience. Second, environment is not stationary as all the agents are learning at the same time (and hence change policies). Third, scale of problem increases significantly with every additional agent. Relevant existing work is extensive and has focussed on dealing with a few good experiences in single-agent RL problems or on scalable approaches for handling non-stationarity in MARL problems. Unfortunately, neither of these approaches (or their extensions) are able to address the problem of sparse good experiences effectively. Therefore, we provide a novel fictitious self imitation approach that is able to simultaneously handle non-stationarity and sparse good experiences in a scalable manner. Finally, we provide a thorough comparison (experimental or descriptive) against relevant cooperative MARL algorithms to demonstrate the utility of our approach.

Editor's note: Alexander Ferguson is CEO and founder of Raleigh and Charlotte-based YourLocalStudio.com, We speak on his growth, the future potential of applying machine learning, and his focus on team building. A pleasure to meet you Alex. Thanks very much for your time and your interest in wanting to chat with me. I started the business directly January 5th, 2015 at 8:30am. I'll never forget it ever--one of the most important dates in my life, honestly.

Mist's Bob Friday: An AI-driven network maximises the user experience through better performance and reliability while lowering IT costs through better efficiencies. Artificial intelligence (AI) – it's a nebulous term that means many things to different people. What is true is that one day in the near future, machines will be likely to possess'human-level' intelligence, providing organisations with efficiencies that they have never seen before. But what role is AI playing inside organisations today, particularly when it comes to providing a good experience for internal users and external customers across their wide area networks? Tech execs gathered in Sydney in September to discuss the benefits of using artificial intelligence technologies inside their wired and wireless networks.

In this paper, we propose a reinforcement learning-based algorithm for trajectory optimization for constrained dynamical systems. This problem is motivated by the fact that for most robotic systems, the dynamics may not always be known. Generating smooth, dynamically feasible trajectories could be difficult for such systems. Using sampling-based algorithms for motion planning may result in trajectories that are prone to undesirable control jumps. However, they can usually provide a good reference trajectory which a model-free reinforcement learning algorithm can then exploit by limiting the search domain and quickly finding a dynamically smooth trajectory. We use this idea to train a reinforcement learning agent to learn a dynamically smooth trajectory in a curriculum learning setting. Furthermore, for generalization, we parameterize the policies with goal locations, so that the agent can be trained for multiple goals simultaneously. We show result in both simulated environments as well as real experiments, for a $6$-DoF manipulator arm operated in position-controlled mode to validate the proposed idea. We compare the proposed ideas against a PID controller which is used to track a designed trajectory in configuration space. Our experiments show that our RL agent trained with a reference path outperformed a model-free PID controller of the type commonly used on many robotic platforms for trajectory tracking.

To seek the origins of Microsoft's interest in artificial intelligence, you need to go way back–well before Amazon, Facebook, and Google were in business, let alone titans of AI. Bill Gates founded Microsoft's research arm in 1991, and AI was an area of investigation from the start. Three years later, in a speech at the National Conference on Artificial Intelligence in Seattle, then-sales chief Steve Ballmer stressed Microsoft's belief in AI's potential and said he hoped that software would someday be smart enough to steer a vehicle. From the start, Microsoft Research (MSR for short) hired more than its fair share of computing's most visionary, accomplished scientists. For a long time, however, it had a reputation for struggling to turn their innovations into features and products that customers wanted. In the '90s, for instance, I recall being puzzled about why its ambitious work in areas such as speech recognition hadn't had a profound effect on Windows and Office. Five years into Satya Nadella's tenure as Microsoft CEO, that stigma is gone.