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. This indicates that reinforcement learning can yield long-term planning with large but achievable scale — without fundamental advances, contrary to our own expectations upon starting the project. Read More
Daily Archives: August 23, 2021
AdapterHub Playground: Simple and Flexible Few-Shot Learning with Adapters
The open-access dissemination of pretrained language models through online repositories has led to a democratization of state-of-the-art natural language processing (NLP) research. This also allows people outside of NLP to use such models and adapt them to specific use-cases. However, a certain amount of technical proficiency is still required which is an entry barrier for users who want to apply these models to a certain task but lack the necessary knowledge or resources. In this work, we aim to overcome this gap by providing a tool which allows researchers to leverage pretrained models without writing a single line of code. Built upon the parameter-efficient adapter modules for transfer learning, our AdapterHub Playground provides an intuitive interface, allowing the usage of adapters for prediction, training and analysis of textual data for a variety of NLP tasks. We present the tool’s architecture and demonstrate its advantages with prototypical use-cases, where we show that predictive performance can easily be increased in a few-shot learning scenario. Finally, we evaluate its usability in a user study. We provide the code and a live interface1. Read More
How Commonsense Knowledge Helps with Natural Language Tasks: A Survey of Recent Resources and Methodologies
In this paper, we give an overview of commonsense reasoning in natural language processing, which requires a deeper understanding of the contexts and usually involves inference over implicit external knowledge. We first review some popular commonsense knowledge bases and commonsense reasoning benchmarks, but give more emphasis on the methodologies, including recent approaches that aim at solving some general natural language problems that take advantage of external knowledge bases. Finally, we discuss some future directions in pushing the boundary of commonsense reasoning in natural language processing. Read More
On the Opportunities and Risks of Foundation Models
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities, and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature. Read More
Rick's Cafe AI 