2021 DeepMind x UCL RL Lecture Series - Policy-Gradient and Actor-Critic methods [9/13] // TRAIN BRAIN

2021 DeepMind x UCL RL Lecture Series - Policy-Gradient and Actor-Critic methods [9/13]

Research Scientist Hado van Hasselt covers policy algorithms that can learn policies directly and actor critic algorithms that combine value predictions for more efficient learning.
Slides: https://dpmd.ai/policygradient
Full video lecture series: https://dpmd.ai/DeepMindxUCL21

DeepMind

Artificial intelligence could be one of humanity's most useful inventions. DeepMind aims to build advanced AI to expand our knowledge and find new answers. By solving this one thing, we believe we could help people solve thousands of problems. We’re a te...

Collaborating for Impact | AI for Science Forum

Google DeepMind

Building the Infrastructure for Success | AI for Science Forum

Google DeepMind

The Polycene Exploring the Opportunity of the Moment with Thomas Friedman | AI for Science Forum

Google DeepMind

[AUDIO DESCRIBED] Using AI to help helping blind and partially-sighted people perceive the world

Google DeepMind

Why AI Creates Better Weather Forecasts

Google DeepMind

Inside Google DeepMind - Sarah

Google DeepMind

Inside Google DeepMind - Annette

Google DeepMind

Inside Google DeepMind - Drew

Google DeepMind

Inside Google DeepMind - Stefano

Google DeepMind

Inside Google DeepMind - Anna

Google DeepMind

Inside Google DeepMind - Deeni

Google DeepMind

Inside Google DeepMind - Dawn

Google DeepMind

Inside Google DeepMind - Kory

Google DeepMind

Inside Google DeepMind - Paige

Google DeepMind

The artists at Novoto Studio share how they are #VisualisingAI

Google DeepMind

How is artist Martina Stiftinger helping create more accurate portrayals of AI? #VisualisingAI

Collaborating for Impact | AI for Science Forum

Building the Infrastructure for Success | AI for Science Forum

The Polycene Exploring the Opportunity of the Moment with Thomas Friedman | AI for Science Forum

Science in the Age of AI | AI for Science Forum

Lessons from CRISPR with Jennifer Doudna | AI for Science Forum

A New Era of Discovery with James Manyika | AI for Science Forum

A New Age of Opportunity | AI for Science Forum

The Ethics of AI Assistants with Iason Gabriel

AI in the classroom with Irina Jurenka

AI: Supercharging Scientific Exploration with Pushmeet Kohli

Gaming, Goats & General Intelligence with Frederic Besse

AI Leaders of Tomorrow: Carlin Foka Takamgno

Decoding Google Gemini with Jeff Dean

AI Safety…Ok Doomer: with Anca Dragan

AI: Your New Creative Muse? with Douglas Eck

Unreasonably Effective AI with Demis Hassabis

Project Astra demo | Solving math problems

Project Astra demo | Recognizing drawings of landmarks

Project Astra demo | Explaining physics drawings

Project Astra demo | Interpreting drawings from literature

Project Astra demo | Memorizing a sequence of objects

Project Astra demo | Explaining parts of a race car

SynthID: A tool for watermarking and identifying AI-generated content

The ultimate collaborator in music | Music AI Sandbox

Using AI to help helping blind and partially-sighted people perceive the world

[AUDIO DESCRIBED] Using AI to help helping blind and partially-sighted people perceive the world

Why AI Creates Better Weather Forecasts

Inside Google DeepMind - Sarah

Inside Google DeepMind - Annette

Inside Google DeepMind - Drew

Inside Google DeepMind - Stefano

Inside Google DeepMind - Anna

Inside Google DeepMind - Deeni

Inside Google DeepMind - Dawn

Inside Google DeepMind - Kory

Inside Google DeepMind - Paige

The artists at Novoto Studio share how they are #VisualisingAI

How is artist Martina Stiftinger helping create more accurate portrayals of AI? #VisualisingAI

How AI is transforming our computing and software

Using machine learning to optimise agriculture in Brazil | AI by you - Vitor’s story

Using AI to manage resources in Africa | AI by you - Arnol’s story

Can AI help to unlock the mysteries of the mind? | AI by you - Weronika’s story

Transforming medicine with AI | AI by you - Sneha’s story

How can AI help us fight climate change? | AI by you - Julia’s story

AI for everyone needs AI by you

Unlocking the mystery of the demon-duck of doom - Unfolded

Welcome to DeepMind: Embarking on one of the greatest adventures in scientific history

Meet John and Rosie, fighting plastic pollution with proteins: Unfolded

How Marcelo and Megan solved a ten year problem in minutes - Unfolded

How EMBL-EBI make AlphaFold’s 200m predictions available - Unfolded

Welcome to DeepMind: Embarking on one of the greatest adventures in scientific history

Match 2: 90 Second Summary - Google DeepMind Challenge Match

Match 5: 90 Second Summary - Google DeepMind Challenge Match 2016

Match 4: 90 Second Summary - Google DeepMind Challenge Match 2016

Match 3: 90 Second Summary - Google DeepMind Challenge Match 2016

Match 1: 90 Second Summary - Google DeepMind Challenge Match 2016

The promise of AI with Demis Hassabis - DeepMind: The Podcast (Season 2, Episode 9)

Fair for all - DeepMind: The Podcast (Season 2, Episode 8)

Me, myself and AI - DeepMind: The Podcast (Season 2, Episode 7)

The road to AGI - DeepMind: The Podcast (Season 2, Episode 5)

Let's get physical - DeepMind: The Podcast (Season 2, Episode 4)

Better together - DeepMind: The Podcast (Season 2, Episode 3)

A breakthrough unfolds - DeepMind: The Podcast (Season 2, Episode 1)

Speaking of intelligence - DeepMind: The Podcast (Season 2, Episode 2)

DeepMind: The Podcast with Hannah Fry - Season 2 coming soon!

2021 DeepMind x UCL RL Lecture Series - Introduction to Reinforcement Learning [1/13]

2021 DeepMind x UCL RL Lecture Series - Exploration & Control [2/13]

2021 DeepMind x UCL RL Lecture Series - MDPs and Dynamic Programming [3/13]

2021 DeepMind x UCL RL Lecture Series - Theoretical Fund. of Dynamic Programming Algorithms [4/13]

2021 DeepMind x UCL RL Lecture Series - Model-free Prediction [5/13]

2021 DeepMind x UCL RL Lecture Series - Model-free Control [6/13]

2021 DeepMind x UCL RL Lecture Series - Function Approximation [7/13]

2021 DeepMind x UCL RL Lecture Series - Planning & models [8/13]

2021 DeepMind x UCL RL Lecture Series - Policy-Gradient and Actor-Critic methods [9/13]

2021 DeepMind x UCL RL Lecture Series - Approximate Dynamic Programming [10/13]

2021 DeepMind x UCL RL Lecture Series - Multi-step & Off Policy [11/13]

2021 DeepMind x UCL RL Lecture Series - Deep Reinforcement Learning #1 [12/13]

2021 DeepMind x UCL RL Lecture Series - Deep Reinforcement Learning #2 [13/13]

NeurIPS 2020: JAX Ecosystem Meetup

AlphaFold: The making of a scientific breakthrough