Posts in category: Deepmind

Despite significant effort, current AI systems pale in their understanding of intuitive physics, in comparison to even very young children. In the present work, we address this AI problem, specifically by drawing on the field of developmental psychology.Read More

Despite significant effort, current AI systems pale in their understanding of intuitive physics, in comparison to even very young children. In the present work, we address this AI problem, specifically by drawing on the field of developmental psychology.Read More

In our recent paper, published in Nature Human Behaviour, we provide a proof-of-concept demonstration that deep reinforcement learning (RL) can be used to find economic policies that people will vote for by majority in a simple game. The paper thus addresses a key challenge in AI research – how to train AI systems that align with human values.Read More

In our recent paper, published in Nature Human Behaviour, we provide a proof-of-concept demonstration that deep reinforcement learning (RL) can be used to find economic policies that people will vote for by majority in a simple game. The paper thus addresses a key challenge in AI research – how to train AI systems that align with human values.Read More

Boxi shares their experiences working as a program specialist on the ethics & society team to support ethical, safe and beneficial AI development, highlighting the importance of interdisciplinary and sociotechnical thinking.Read More

Read More

Avishkar Bhoopchand, a research engineer on the Game Theory and Multi-agent team, shares his journey to DeepMind and how he’s working to raise the profile of deep learning across Africa.Read More

We present BYOL-Explore, a conceptually simple yet general approach for curiosity-driven exploration in visually-complex environments. BYOL-Explore learns a world representation, the world dynamics, and an exploration policy all-together by optimizing a single prediction loss in the latent space with no additional auxiliary objective. We show that BYOL-Explore is effective in DM-HARD-8, a challenging partially-observable continuous-action hard-exploration benchmark with visually-rich 3-D environments.Read More

We present BYOL-Explore, a conceptually simple yet general approach for curiosity-driven exploration in visually-complex environments. BYOL-Explore learns a world representation, the world dynamics, and an exploration policy all-together by optimizing a single prediction loss in the latent space with no additional auxiliary objective. We show that BYOL-Explore is effective in DM-HARD-8, a challenging partially-observable continuous-action hard-exploration benchmark with visually-rich 3-D environments.Read More

According to empirical evidence from prior works, utility degradation in DP-SGD becomes more severe on larger neural network models – including the ones regularly used to achieve the best performance on challenging image classification benchmarks. Our work investigates this phenomenon and proposes a series of simple modifications to both the training procedure and model architecture, yielding a significant improvement on the accuracy of DP training on standard image classification benchmarks.Read More