In the first lecture of the series, Research Scientist Hado introduces the course and explores the fascinating connection between reinforcement learning and artificial intelligence: dpmd.ai/RLseries1
In lecture two, Research Scientist Hado explains why it's important for learning agents to balance exploring and exploiting acquired knowledge at the same time: dpmd.ai/RLseries2
In the third lecture, Research Scientist Diana shows us how to solve MDPs with dynamic programming to extract accurate predictions and good control policies: dpmd.ai/RLseries3
In lecture four, Diana covers dynamic programming algorithms as contraction mappings, looking at when and how they converge to the right solutions: dpmd.ai/RLseries4
In part two of the model-free lecture, Hado explains how to use prediction algorithms for policy improvement, leading to algorithms - like Q-learning - that can learn good behaviour policies from sampled experience: dpmd.ai/RLseries6
In this lecture, Hado explains how to combine deep learning with reinforcement learning for deep reinforcement learning. He looks at the properties and difficulties that arise when combining function approximation with RL algorithms: dpmd.ai/RLseries7
In this lecture, Research Engineer Matteo explains how to learn and use models, including algorithms like Dyna and Monte-Carlo tree search (MCTS): dpmd.ai/RLseries8
We’re announcing a research collaboration with @CFS_energy, one of the world’s leading nuclear fusion companies.
Together, we’re helping speed up the development of clean, safe, limitless fusion power with AI. ⚛️
Fusion powers the sun, but here on Earth, one approach involves controlling a super-hot, ionized gas called plasma inside a tokamak machine.
To predict power generation, we need to simulate how heat, electric current and matter flow through the core of a plasma and interact with systems around it. This is where TORAX comes in.
TORAX is our open-source plasma simulator allowing CFS to run millions of virtual experiments to test plans for their tokamak, SPARC.
Using reinforcement learning, we’re now rapidly identifying the most efficient paths for it to generate more power than it consumes - a landmark achievement known as crossing "breakeven."
We’re rolling out Veo 3.1, our updated video generation model, alongside improved creative controls for filmmakers, storytellers, and developers - many of them with audio. 🧵
🎥 Introducing Veo 3.1
It brings a deeper understanding of the narrative you want to tell, capturing textures that look and feel even more real, and improved image-to-video capabilities.
🖼️ Ingredients to video
Give multiple reference images with different people and objects, and watch how Veo integrates these into a fully-formed scene - complete with sound.
We’re announcing a major advance in the study of fluid dynamics with AI 💧 in a joint paper with researchers from @BrownUniversity, @nyuniversity and @Stanford.
Equations to describe fluid motion - like airflow lifting an airplane wing or the swirling vortex of a hurricane - can sometimes "break," predicting impossible, infinite values.
These "singularities" are a huge mystery in mathematical physics.
We used a new AI-powered method to discover new families of unstable “singularities” across three different fluid equations.
A clear and unexpected pattern emerged: as the solutions become more unstable, one of the key properties falls very close to a straight line.
This suggests a new, underlying structure to these equations that was previously invisible.
We’re helping to unlock the mysteries of the universe with AI. 🌌
Our novel Deep Loop Shaping method
published in @ScienceMagazine could help astronomers observe more events like collisions and mergers of black holes in greater detail, and gather more data about rare space phenomena. 🧵
Astronomers already know a lot about the smallest and largest black holes. ⚫
But we have limited data on intermediate-mass black holes, and the observatories we use to measure their gravitational waves need improved control, and expanded reach. ↓ goo.gle/47oalza
⚡This is where Deep Loop Shaping comes in.
Developed in collaboration with @LIGO Laser Interferometer Gravitational-Wave Observatory, @CalTech and the Gran Sasso Science Institute, it reduces noise and improves control in an observatory’s feedback system - helping stabilize components used for measuring gravitational waves.
Image generation with Gemini just got a bananas upgrade and is the new state-of-the-art image generation and editing model. 🤯
From photorealistic masterpieces to mind-bending fantasy worlds, you can now natively produce, edit and refine visuals with new levels of reasoning, control and creativity.
A quick dive into Gemini 2.5 Flash’s capabilities 🧵
🎯 Character consistency
Give the model reference images and it can produce new visuals that maintain a character, subject or object’s likeness across different poses, lighting, environments or styles - helping you create more compelling, narrative-driven work.
🔄 Design application
Looking to apply a specific artistic style, design, or texture? 2.5 Flash can now easily transfer this from one image to another while preserving the previous subject's form and details.
Our new state-of-the-art AI model Aeneas transforms how historians connect the past. 📜
Ancient inscriptions often lack context – it's like solving a puzzle with 90% of the pieces lost to time. It helps researchers interpret and situate inscriptions in their past context. 🧵
By transforming each ancient text into a unique historical fingerprint, Aeneas can identify similarities across 176,000 Latin inscriptions.
In our study, historians found these ‘parallels’ to be helpful research starting points 9 out of 10 times - improving their confidence by 44%.
We tested Aeneas on the Res Gestae Divi Augusti – one of the most debated inscriptions.
Without prior knowledge, it successfully mapped out the leading scholarly theories on its dating, showing how AI can help model history in a quantitative way. 📊