Posts in category: Deepmind

There has been rapidly growing interest in developing methods for meta-learning within deep RL. Although there has been substantive progress toward such ‘meta-reinforcement learning,’ research in this area has been held back by a shortage of benchmark tasks. In the present work, we aim to ease this problem by introducing (and open-sourcing) Alchemy, a useful new benchmark environment for meta-RL, along with a suite of analysis tools.Read More

In this work, we examine what aspects of multimodal transformers – attention, losses, and pretraining data – are important in their success at multimodal pretraining. We find that Multimodal attention, where both language and image transformers attend to each other, is crucial for these models’ success. Models with other types of attention (even with more depth or parameters) fail to achieve comparable results to shallower and smaller models with multimodal attention.Read More

Planning winning strategies in unknown environments is a step forward in the pursuit of general-purpose algorithms.Read More

We first create a simulated environment, the Playroom, in which virtual robots can engage in a variety of interesting interactions by moving around, manipulating objects, and speaking to each other. The Playroom’s dimensions can be randomised as can its allocation of shelves, furniture, landmarks like windows and doors, and an assortment of children’s toys and domestic objects. The diversity of the environment enables interactions involving reasoning about space and object relations, ambiguity of references, containment, construction, support, occlusion, partial observability. We embedded two agents in the Playroom to provide a social dimension for studying joint intentionality, cooperation, communication of private knowledge, and so on.Read More

Here we share our experience of working with JAX, outline why we find it useful for our AI research, how we are supporting JAX development, and give an overview of the ecosystem we are building to support researchers everywhere.Read More

In a major scientific advance, the latest version of our AI systemAlphaFoldhas been recognised as a solution to the protein folding problem by the organisers of the biennial Critical Assessment of protein Structure Prediction (CASP).Read More

We present our use of Unity, a widely recognised and comprehensive game engine, to create more diverse, complex, virtual simulations. We describe the concepts and components developed to simplify the authoring of these environments, intended for use predominantly in the field of reinforcement learning.Read More

Read More

Weve developed a new neural network architecture, the Fermionic Neural Network or FermiNet, which is well-suited to modeling the quantum state of large collections of electrons, the fundamental building blocks of chemical bonds.Read More

Read More