We've created an AI system, OpenAI Five, which has started to defeat amateur human teams. This video contains an overview of our system, some example gameplay, and professional caster Blitz's analysis of our bot, as we start to gear up for playing a professional team at this year's Dota world championships, The International. See our blog post for more details: https://blog.openai.com/openai-five.

The discovery of new materials can bring enormous societal and technological progress. In this context, exploring completely the large space of potential materials is computationally intractable. Here, we review methods for achieving inverse design, which aims to discover tailored materials from the starting point of a particular desired functionality. Recent advances from the rapidly growing field of artificial intelligence, mostly from the subfield of machine learning, have resulted in a fertile exchange of ideas, where approaches to inverse molecular design are being proposed and employed at a rapid pace. Among these, deep generative models have been applied to numerous classes of materials: rational design of prospective drugs, synthetic routes to organic compounds, and optimization of photovoltaics and redox flow batteries, as well as a variety of other solid-state materials.

Subcommittee on Research and Technology and Subcommittee on Energy Hearing - Artificial Intelligence - June 26th, 2018 Dr. Tim Persons, chief scientist, GAO Mr. Greg Brockman, co-founder and chief technology officer, OpenAI Dr. Fei-Fei Li, chairperson of the board and co-founder, AI4ALL OpenAI was founded by Elon Musk and Sam Altman

Our team of five neural networks, OpenAI Five, has started to defeat amateur human teams at Dota 2. While today we play with restrictions, we aim to beat a team of top professionals at The International in August subject only to a limited set of heroes. We may not succeed: Dota 2 is one of the most popular and complex esports games in the world, with creative and motivated professionals who train year-round to earn part of Dota's annual $40M prize pool (the largest of any esports game). OpenAI Five plays 180 years worth of games against itself every day, learning via self-play. It trains using a scaled-up version of Proximal Policy Optimization running on 256 GPUs and 128,000 CPU cores -- a larger-scale version of the system we built to play the much-simpler solo variant of the game last year. Using a separate LSTM for each hero and no human data, it learns recognizable strategies.

Fuzzing is a commonly used technique designed to test software by automatically crafting program inputs. Currently, the most successful fuzzing algorithms emphasize simple, low-overhead strategies with the ability to efficiently monitor program state during execution. Through compile-time instrumentation, these approaches have access to numerous aspects of program state including coverage, data flow, and heterogeneous fault detection and classification. However, existing approaches utilize blind random mutation strategies when generating test inputs. We present a different approach that uses this state information to optimize mutation operators using reinforcement learning (RL). By integrating OpenAI Gym with libFuzzer we are able to simultaneously leverage advancements in reinforcement learning as well as fuzzing to achieve deeper coverage across several varied benchmarks. Our technique connects the rich, efficient program monitors provided by LLVM Santizers with a deep neural net to learn mutation selection strategies directly from the input data. The cross-language, asynchronous architecture we developed enables us to apply any OpenAI Gym compatible deep reinforcement learning algorithm to any fuzzing problem with minimal slowdown.

Since the early days of machine learning, artificial intelligence scenarios have faced with two big challenges in order to experience mainstream adoption. First, we have the data efficiency problem that requires machine or deep learning models to be trained using large and accurate datasets which, as we know, are really expensive to build and maintain. Secondly, we have the generalization problem which AI agents face in order to build new knowledge that is different from the training data. Humans, by contrast, are incredibly efficient learning with minimum supervision and rapidly generalizing knowledge from a few data examples. Generative models are one of the deep learning disciplines that focuses on addressing the two challenges mentioned above.

Many deep models have been recently proposed for anomaly detection. This paper presents comparison of selected generative deep models and classical anomaly detection methods on an extensive number of non--image benchmark datasets. We provide statistical comparison of the selected models, in many configurations, architectures and hyperparamaters. We arrive to conclusion that performance of the generative models is determined by the process of selection of their hyperparameters. Specifically, performance of the deep generative models deteriorates with decreasing amount of anomalous samples used in hyperparameter selection. In practical scenarios of anomaly detection, none of the deep generative models systematically outperforms the kNN.

We introduce a deep generative model for functions. Our model provides a joint distribution p(f, z) over functions f and latent variables z which lets us efficiently sample from the marginal p(f) and maximize a variational lower bound on the entropy H(f). We can thus maximize objectives of the form E_{f~p(f)}[R(f)] + c*H(f), where R(f) denotes, e.g., a data log-likelihood term or an expected reward. Such objectives encompass Bayesian deep learning in function space, rather than parameter space, and Bayesian deep RL with representations of uncertainty that offer benefits over bootstrapping and parameter noise. In this short paper we describe our model, situate it in the context of prior work, and present proof-of-concept experiments for regression and RL.

We introduce Glow, a reversible generative model which uses invertible 1x1 convolutions. It extends previous work on reversible generative models and simplifies the architecture. Our model can generate realistic high resolution images, supports efficient sampling, and discovers features that can be used to manipulate attributes of data. We're releasing code for the model and an online visualization tool so people can explore and build on these results. The model isn't given attribute labels at training time, yet it learns a latent space where certain directions correspond to changes in attributes like beard density, age, hair color, and so on.

On Monday, non-profit AI research company OpenAI published a blog post about OpenAI Five, a group of five neural networks designed to work as a team while playing the real-time computer strategy game called Dota 2. According to the post, OpenAI Five can now beat a team of five human amateur players at the game, albeit with specific restrictions placed on gameplay. In August, it will attempt to beat a team of professional Dota 2 players at The International (TI), an annual Dota 2 tournament hosted by the game's developer, Valve Corporation.