We propose a simple, general and effective technique, Reward Randomization for discovering diverse strategic policies in complex multi-agent games. Combining reward randomization and policy gradient, we derive a new algorithm, Reward-Randomized Policy Gradient (RPG). RPG is able to discover multiple distinctive human-interpretable strategies in challenging temporal trust dilemmas, including grid-world games and a real-world game Agar.io, Furthermore, with the set of diverse strategies from RPG, we can (1) achieve higher payoffs by fine-tuning the best policy from the set; and (2) obtain an adaptive agent by using this set of strategies as its training opponents. Games have been a long-standing benchmark for artificial intelligence, which prompts persistent technical advances towards our ultimate goal of building intelligent agents like humans, from Shannon's initial interest in Chess (Shannon, 1950) and IBM DeepBlue (Campbell et al., 2002), to the most recent deep reinforcement learning breakthroughs in Go (Silver et al., 2017), Dota II (OpenAI et al., 2019) and Starcraft (Vinyals et al., 2019). Hence, analyzing and understanding the challenges in various games also become critical for developing new learning algorithms for even harder challenges. Most recent successes in games are based on decentralized multi-agent learning (Brown, 1951; Singh et al., 2000; Lowe et al., 2017; Silver et al., 2018), where agents compete against each other and optimize their own rewards to gradually improve their strategies. Despite the empirical success of these algorithms, a fundamental question remains largely unstudied in the field: even if an MARL algorithm converges to an NE, which equilibrium will it converge to? The existence of multiple NEs is extremely common in many multi-agent games. Discovering as many NE strategies as possible is particularly important in practice not only because different NEs can produce drastically different payoffs but also because when facing unknown players who are trained to play an NE strategy, we can gain advantage by identifying which NE strategy the opponent is playing and choosing the most appropriate response. Unfortunately, in many games where multiple distinct NEs exist, the popular decentralized policy gradient algorithm (PG), which has led to great successes in numerous games including Dota II and Stacraft, always converge to a particular NE with non-optimal payoffs and fail to explore more diverse modes in the strategy space. Consider an extremely simple example, a 2-by-2 matrix game Stag-Hunt (Rousseau, 1984; Skyrms, 2004), where two pure strategy NEs exist: a "risky" cooperative equilibrium with the highest payoff for both agents and a "safe" non-cooperative equilibrium with strictly lower payoffs.

Do mass media influence people's opinion of other countries? Using BERT, a deep neural network-based natural language processing model, we analyze a large corpus of 267,907 China-related articles published by The New York Times since 1970. We then compare our output from The New York Times to a longitudinal data set constructed from 101 cross-sectional surveys of the American public's views on China. We find that the reporting of The New York Times on China in one year explains 54% of the variance in American public opinion on China in the next. Our result confirms hypothesized links between media and public opinion and helps shed light on how mass media can influence public opinion of foreign countries.

This upload contains the neural networks used in the paper "Improving filling level classification with adversarial training". The networks are already pre-trained on the 3 splits (S1, S2, S3) of the C-CCM dataset, using six different training strategies. The networks are implemented in PyTorch. More information regarding the C-CCM dataset can be found here: https://corsmal.eecs.qmul.ac.uk/filling.html The CCM_Filling_Level_Pretrained_Models.zip file contains: 3 folders (S1, S2, S3) that correspond to the different dataset splits Each of S1, S2, S3 folders contains 6 subfolders (ST, AT, ST-FT, ST-AFT, AT-FT, AT-AFT) which correspond to the different training strategies used in the paper. Each of the ST, AT, ..., AT-AFT subfolders contains a PyTorch file named last.t7. This is the PyTorch ResNet-18 model that is trained on the corresponding split (S1/S2/S3) using the corresponding training strategy (ST, AT, ..., AT-AFT). A Python example script for loading the models is also provided (load_model.py).

Last November, Apple ran into trouble after customers pointed out on Twitter that its credit card service was discriminating against women. David Heinemeir Hansson, the creator of Ruby on Rails, called Apple Card a sexist program. "Apple's black box algorithm thinks I deserve 20x the credit limit [my wife] does," he tweeted. The success of deep learning in the past decade has increased interest in the field of artificial intelligence. But the rising popularity of AI has also highlighted some of the key problems of the field, including the "black box problem," the challenge of making sense of the way complex machine learning algorithms make decisions.

Efforts to automate the analysis of electrocardiograms (ECGs) date back to the 1950s when researchers first converted ECG signals from analog to digital form, enabling the subsequent creation of algorithms that could be used in computer-interpreted ECG (CIE).1,2 With continued technological advances, the use of CIE has become so common that more than 100 million ECGS are interpreted by computer each year in the United States.2 However, conventional CIE models require over-reading by a physician, and despite these checks, certain ECG features may be missed. A growing body of research highlights the potential value of deep learning-based CIE, which could detect features that may be overlooked or undetectable by a physician reader.3,4 "Deep learning is a subfield of machine learning which tends to solve a problem end to end to eliminate the need for domain expertise and to fully explore ECG features from raw ECG data," according to an article co-authored by Shijie Zhou, PhD, assistant research scientist in the department of biomedical engineering and the Alliance for Cardiovascular Diagnostic and Treatment Innovation (ADVANCE) Institute at Johns Hopkins University in Baltimore.5 "Deep-learning models use neural networks to capture only the most important features from the input data and disregard redundant input features by means of network pruningto maintain model accuracy."

Following a range of studies showing promise for the classification of arrhythmias using deep-learning algorithms based on single-lead ECG data, …

In 1997, an AI beat a human world chess champion for the first time in history (it was IBM's Deep Blue playing Garry Kasparov). Fourteen years later, in 2011, IBM's Watson beat two winners of Jeopardy! In late 2017, DeepMind's AlphaZero reached superhuman levels of play in three board games (chess, go and shogi) in just 24 hours of self-learning without any human intervention, i.e. it just played itself. Some of the people who have played against it say that the creativity of its moves make it seem more like an alien that a computer program. But despite all that, in 2019 nobody has yet designed anything that can go into a strange kitchen and fry an egg. Are our machines truly intelligent? The fact is that today AI can solve ever more complex specific problems with a level of reliability and speed beyond our reach at an unbeatable cost, but it fails spectacularly in the face of any challenge for which it has not been programmed.

Despite years of hype, virtual reality headsets have yet to topple TV or computer screens as the go-to devices for video viewing. One reason: VR can make users feel sick. Nausea and eye strain can result because VR creates an illusion of 3D viewing although the user is in fact staring at a fixed-distance 2D display. The solution for better 3D visualization could lie in a 60-year-old technology remade for the digital world: holograms. Holograms deliver an exceptional representation of 3D world around us.

Deep learning (DL) algorithms have, over the past decade, emerged as the most competitive image recognition algorithms; however, they are by default "black box" algorithms: it is difficult to explain why they make a specific prediction. Why is that an issue? Users of ML models often want the ability to interpret which parts of the image led to the algorithm's prediction for many reasons: Motivated by these use cases, during the last decade, researchers developed many different methods to open the "black box" of deep learning, aiming to make underlying models more explainable. Some methods are specific for certain kinds of algorithms, while some are general. Some are fast, and some are slow.

What if I tell you that an entire short sci-fi film has been written by an AI bot built on LSTM recurrent neural network, and it has even received positive reviews and critics, Surprised?! well, I'm sure you are because that's what I felt watching "Sunspring" for the first time, I mean I know it can't be compared to Steven Spielberg's or Alex Garland's screenwriting quality but no wonder if in the next few years AI bots will compete against them in the Academy Awards. Indeed, we should no longer be surprised by what artificial intelligence is capable of in order to flip our world upside down, making it a better, "easier", and most comfortable place to live in. From all of the AI subfields, in my opinion, NLP has the coolest and most exciting applications. One of them is text generation that we should have a deep look at it. In this article, I will briefly explain how RNN and LSTM work and how we can generate texts using LSTM in Python.