In March 2016, Deepmind's AlphaGo beat 18 times world champion Go player Lee Sedol 4–1 in a series watched by over 200 million people. A machine had learnt a super-human strategy for playing Go, a feat previously thought impossible, or at the very least, at least a decade away from being accomplished. This in itself, was a remarkable achievement. However, on 18th October 2017, DeepMind took a giant leap further. The paper'Mastering the Game of Go without Human Knowledge' unveiled a new variant of the algorithm, AlphaGo Zero, that had defeated AlphaGo 100–0.

Elon Musk has put a lot of thought into the harsh realities and wild possibilities of artificial intelligence (AI). These considerations have left him convinced that we need to merge with machines if we're to survive, and he's even created a startup dedicated to developing the brain-computer interface (BCI) technology needed to make that happen. But despite the fact that his very own lab, OpenAI, has created an AI capable of teaching itself, Musk recently said that efforts to make AI safe only have "a five to 10 percent chance of success." Musk shared these less-than-stellar odds with the staff at Neuralink, the aforementioned BCI startup, according to recent Rolling Stone article. Despite Musk's heavy involvement in the advancement of AI, he's openly acknowledged that the technology brings with it not only the potential for, but the promise of serious problems.

Want to watch this again later? Sign in to add this video to a playlist. Report Need to report the video? Sign in to report inappropriate content. Report Need to report the video?

This nascent AI technique – which requires no input data, substantially less computing power, and in which the evolutionary-like AI learns from itself – could soon evolve to enable its application to real-world problems in the natural sciences. Collaboration with Earth scientists to identify the systems – from climate science, materials science, biology, and other areas – which can be codified to apply reinforcement learning for scientific progress and discovery is vital. For example, DeepMind co-founder, Demis Hassabis, has suggested that in materials science, a descendant of AlphaGo Zero could be used to search for a room temperature superconductor – a hypothetical substance that allows for incredibly efficient energy systems.

We present a simple generative framework for learning to predict previously unseen classes, based on estimating class-attribute-gated class-conditional distributions. We model each class-conditional distribution as an exponential family distribution and the parameters of the distribution of each seen/unseen class are defined as functions of the respective observed class attributes. These functions can be learned using only the seen class data and can be used to predict the parameters of the class-conditional distribution of each unseen class. Unlike most existing methods for zero-shot learning that represent classes as fixed embeddings in some vector space, our generative model naturally represents each class as a probability distribution. It is simple to implement and also allows leveraging additional unlabeled data from unseen classes to improve the estimates of their class-conditional distributions using transductive/semi-supervised learning. Moreover, it extends seamlessly to few-shot learning by easily updating these distributions when provided with a small number of additional labelled examples from unseen classes. Through a comprehensive set of experiments on several benchmark data sets, we demonstrate the efficacy of our framework.

OpenAI's mission is to build safe artificial general intelligence (AGI) and ensure AGI's benefits are as widely and evenly distributed as possible. As a non-profit AI research company, they focus on long-term research, working on problems that require fundamental advances in AI capabilities. OpenAI runs Kubernetes for their deep learning research because Kubernetes can provide a fast iteration cycle, scalability, and a lack of boilerplate, which makes it ideal for most of OpenAI's experiments. They currently operate several Kubernetes clusters (some in the cloud and some on physical hardware), the largest of which they pushed to over 2,500 nodes. Their Kubernetes cluster runs in Azure on a combination of D15v2 and NC24 VMs.

Right on cue, this past week heralded in an announcement of OpenAI, a new non-profit started by a number of tech luminaries to spearhead AI research that is publicly accessible. The motivation is that apparently these scions of capitalism lose faith in Adam Smith's invisible hand when it comes to AI R&D. Musk continues to promote the idea that AI will be humanity's largest existential threat. Challenging this view, the HBR asks if "OpenAI [is] Solving the Wrong Problem", pointing to the implied lack of trust in capitalism. This is similar to my own parry: that the biggest existential threat to humanity is humanity.

Our code is based off of code from OpenAI, who we thank. The original code and related paper from OpenAI can be found here. The repo has been modified to run both ES and our algorithms, including our Deep Genetic Algorithm (DeepGA) locally and on AWS. Note: The Humanoid experiment depends on Mujoco. If you plan to use the mujoco env, make sure to follow mujoco-py's readme about how to install mujoco correctly The extra folder holds the XML specification file for the Humanoid Locomotion with Deceptive Trap domain used in https://arxiv.org/abs/1712.06560.

OpenAI, a $1 billion (£687 million) artificial intelligence company backed by Elon Musk, has built a "gym" where developers can train their AI systems to get smarter. Using OpenAI's open source toolkit, available for download now, developers can access "environments" where they can test their AI bots. The OpenAI Gym, currently in beta, provides a number of environments, including more than 50 Atari games, such as "Space Invaders," "Pong," "Asteroids" and "Pac-Man". Developers can also test their AIs on board games like Go, which was recently mastered by an agent built by London startup Google DeepMind. "Over time, we plan to greatly expand this collection of environments," wrote OpenAI's Greg Brockman and John Schulman in a blog post.

The machine-learning models scored 82.44 on the Stanford Question Answering Dataset, a large-scale reading comprehension test with more than 100,000 questions, compared with 82.304 by humans. Stanford tests are used by several international universities and global technology firms, including Google, Facebook, IBM and Microsoft, to determine whether their machine learning models are able to answer the questions in the data set. Machines have already bested humans in complex games like chess, where skills such as infallible memory and raw computing power align with the intrinsic capabilities of bots. In December last year (2017), DeepMind, Google's artificial intelligence programme, was able to win a game of chess after first learning how to play the game. Where computers have surpassed human ability before in games of chess by using pre-conditioned programming, DeepMind's AlphaZero program experimented by playing games against itself until it had discerned the effectiveness of all possible moves.