Post

How to get URL link on X (Twitter) App

On the Twitter thread, click on or icon on the bottom
Click again on or Share Via icon
Click on Copy Link to Tweet
Paste it above and click "Unroll Thread"!
More info at Twitter Help

Google DeepMind

Sep 9, 2021 • 10 tweets • 9 min read • Read on X

Scrolly

@ai_ucl

Introducing the '21 DeepMind x @ai_ucl Reinforcement Learning Lecture Series, a comprehensive introduction to modern RL.

Follow along with our researchers are they explore Markov Decision Processes, sample-based learning algorithms & much more: dpmd.ai/2021RLseries 1/2

@YouTube

Also find the full series via the DeepMind @YouTube channel: dpmd.ai/DeepMindxUCL21

@ai_ucl

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

#DeepMindxUCL @ai_ucl

@ai_ucl

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

#DeepMindxUCL @ai_ucl

@ai_ucl

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

#DeepMindxUCL @ai_ucl

@ai_ucl

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

#DeepMindxUCL @ai_ucl

@ai_ucl

In this lecture, Hado explores model-free prediction and its relation to Monte Carlo and temporal difference algorithms: dpmd.ai/RLseries5

#DeepMindxUCL @ai_ucl

@ai_ucl

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

#DeepMindxUCL @ai_ucl

@ai_ucl

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

#DeepMindxUCL @ai_ucl

@ai_ucl

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

#DeepMindxUCL @ai_ucl

• • •

Missing some Tweet in this thread? You can try to force a refresh

This Thread may be Removed Anytime!

Twitter may remove this content at anytime! Save it as PDF for later use!

More from @GoogleDeepMind

Google DeepMind

@GoogleDeepMind

May 19

We’re dropping Gemini Omni: our first step towards a model that can create anything from anything - starting with video.

It combines Gemini’s intelligence with our generative media systems - representing a leap forward in world understanding, multimodality, and editing 🧵

Omni brings together an improved understanding of physics with Gemini's knowledge of history, biology, and culture, bridging the gap from photorealism to meaningful storytelling.

Actions have consequences, environments respond to events, and narratives evolve logically.

🔘 Define a character once - then place them in any scene, and they’ll stay consistent across locations, actions and lighting.

🔘 Apply styles, motion, or effects by using input references, or just describe it with natural language.

Read 5 tweets

Google DeepMind

@GoogleDeepMind

May 12

We’re reimagining a 50-year-old interface - the mouse pointer - with AI. 🖱️

These experimental demos show how people can intuitively direct Gemini on their screens using motion, speech, and natural shorthand to get things done 🧵

With an AI-enabled pointer, help is always available where you’re working - without having to detour to additional apps. 📲

Point at a PDF and request bullet points for an email, hover over a table to ask for a pie chart, or highlight a recipe and simply say: "double these ingredients."

Current models require precise instructions, but our AI-enabled pointer removes that burden. 💡

By "seeing" what’s under your cursor, it instantly understands the specific word, image, or code block you need help with.

Read 6 tweets

Google DeepMind

@GoogleDeepMind

Nov 17, 2025

Weather affects everything and everyone. Our latest AI model developed with @GoogleResearch is helping us better predict it. ⛅

WeatherNext 2 is our most advanced system yet, able to generate more accurate and higher-resolution global forecasts. Here’s what it can do - and why it matters 🧵

A core challenge in weather prediction is capturing the full range of outcomes.

With WeatherNext 2, we can explore hundreds of possibilities in less than a minute from a single starting point. This would require hours on a supercomputer using physics-based models.

The model’s improved performance is enabled by a new approach called a Functional Generative Network, which can generate the full range of possible forecasts in a single step.

We added targeted randomness directly into the architecture, allowing it to explore a wide range of sensible weather scenarios.

Read 6 tweets

Google DeepMind

@GoogleDeepMind

Nov 13, 2025

SIMA 2 is our most capable AI agent for virtual 3D worlds. 👾🌐

Powered by Gemini, it goes beyond following basic instructions to think, understand, and take actions in interactive environments – meaning you can talk to it through text, voice, or even images. Here’s how 🧵

Advanced reasoning 🧠

We trained SIMA 2 to achieve high-level goals in a wide array of games – allowing it to perform complex reasoning and independently plan how to accomplish tasks.

It acts like a collaborative partner that can explain its intentions and answer questions about its behavior.

Generalization ☂️

SIMA 2 is now far better at carrying out detailed instructions, even in worlds it's never seen before.

It can transfer learned concepts like “mining” in one game and apply it to “harvesting” in another – connecting the dots between similar tasks.

It even navigated unseen environments created in real-time by our Genie 3 model.

Read 5 tweets

Google DeepMind

@GoogleDeepMind

Oct 16, 2025

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."

Read 5 tweets

Google DeepMind

@GoogleDeepMind

Oct 15, 2025

Veo is getting a major upgrade. 🚀

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.