Publications (12)
Temporal Difference Variational Auto-Encoder
Karol Gregor, George Papamakarios, Frederic Besse +2
To act and plan in complex environments, we posit that agents should have a mental simulator of the world with three characteristics: (a) it should build an abstract state represen…
Learning and Querying Fast Generative Models for Reinforcement Learning
Lars Buesing, Theophane Weber, Sebastien Racaniere +8
A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models. We show that carefully designed generative mo…
TF-Replicator: Distributed Machine Learning for Researchers
Peter Buchlovsky, David Budden, Dominik Grewe +9
We describe TF-Replicator, a framework for distributed machine learning designed for DeepMind researchers and implemented as an abstraction over TensorFlow. TF-Replicator simplifie…
Convolution by Evolution: Differentiable Pattern Producing Networks
Chrisantha Fernando, Dylan Banarse, Malcolm Reynolds +5
In this work we introduce a differentiable version of the Compositional Pattern Producing Network, called the DPPN. Unlike a standard CPPN, the topology of a DPPN is evolved but th…
Causally Correct Partial Models for Reinforcement Learning
Danilo J. Rezende, Ivo Danihelka, George Papamakarios +11
In reinforcement learning, we can learn a model of future observations and rewards, and use it to plan the agent's next actions. However, jointly modeling future observations can b…
Scaling Instructable Agents Across Many Simulated Worlds
SIMA Team, Maria Abi Raad, Arun Ahuja +91
Building embodied AI systems that can follow arbitrary language instructions in any 3D environment is a key challenge for creating general AI. Accomplishing this goal requires lear…
Towards Conceptual Compression
Karol Gregor, Frederic Besse, Danilo Jimenez Rezende +2
We introduce a simple recurrent variational auto-encoder architecture that significantly improves image modeling. The system represents the state-of-the-art in latent variable mode…
Self-Organizing Intelligent Matter: A blueprint for an AI generating algorithm
Karol Gregor, Frederic Besse
We propose an artificial life framework aimed at facilitating the emergence of intelligent organisms. In this framework there is no explicit notion of an agent: instead there is an…
Shaping Belief States with Generative Environment Models for RL
Karol Gregor, Danilo Jimenez Rezende, Frederic Besse +3
When agents interact with a complex environment, they must form and maintain beliefs about the relevant aspects of that environment. We propose a way to efficiently train expressiv…
Encoding Spatial Relations from Natural Language
Tiago Ramalho, Tomáš KoÄiský, Frederic Besse +5
Natural language processing has made significant inroads into learning the semantics of words through distributional approaches, however representations learnt via these methods fa…
SIMA 2: A Generalist Embodied Agent for Virtual Worlds
SIMA team, Adrian Bolton, Alexander Lerchner +63
We introduce SIMA 2, a generalist embodied agent that understands and acts in a wide variety of 3D virtual worlds. Built upon a Gemini foundation model, SIMA 2 represents a signifi…
Learning models for visual 3D localization with implicit mapping
Dan Rosenbaum, Frederic Besse, Fabio Viola +2
We consider learning based methods for visual localization that do not require the construction of explicit maps in the form of point clouds or voxels. The goal is to learn an impl…