David Silver - Deep Reinforcement Learning from AlphaGo to AlphaStar

Показать описание

Recently, self-learning systems have achieved remarkable success in several challenging problems for artificial intelligence, by combining reinforcement learnng with deep neural networks. In this talk, I describe the ideas and algorithms that led to AlphaGo: the first program to defeat a human champion in the game of Go; AlphaZero: which learned, from scratch, to also defeat the world computer champions in chess and shogi; and AlphaStar: the first program to defeat a human champion in the real-time strategy game of StarCraft.

Bio: David Silver is a principal research scientist at DeepMind and a professor at University College London. David's work focuses on artificially intelligent agents based on reinforcement learning. David co-led the project that combined deep learning and reinforcement learning to play Atari games directly from pixels (Nature 2015). He also led the AlphaGo project, culminating in the first program to defeat a top professional player in the full-size game of Go (Nature 2016), and the AlphaZero project, which learned by itself to defeat the world's strongest chess, shogi and Go programs (Nature 2017, Science 2018). Most recently, he co-led the AlphaStar project, which led to the world's first grandmaster level StarCraft player (Nature 2019). His work has been recognised by the Marvin Minsky award, Mensa Foundation Prize, and Royal Academy of Engineering Silver Medal.

*Sponsors*
Man AHL: At Man AHL, we mix machine learning, computer science and engineering with terabytes of data to invest billions of dollars every day.

London Machine Learning Meetup

Рекомендации по теме

Комментарии

This is so high level. Thanks so much for sharing, David!

haraldgnaf

What would happen if two machines with the same version of alphastar are made to play against each other? Can we predict if the first one that moves will always win. Assume they are both are use same random weights with the same seed.

ChuckChekuri

I would like to add, did you even think about putting two programs in the same Arena with or without human players😎🤓 I'm just asking as a human

timjohnson

David Silver - Deep Reinforcement Learning from AlphaGo to AlphaStar

What is Deep Reinforcement Learning? (David Silver, DeepMind) | AI Podcast Clips

RL Course by David Silver - Lecture 1: Introduction to Reinforcement Learning

RL Course by David Silver - Lecture 2: Markov Decision Process

David Silver - Deep Reinforcement Learning from AlphaGo to AlphaStar

Keynote David Silver NIPS 2017 Deep Reinforcement Learning Symposium AlphaZero

RL Course by David Silver - Lecture 3: Planning by Dynamic Programming

RL Course by David Silver - Lecture 4: Model-Free Prediction

RL Course by David Silver - Lecture 7: Policy Gradient Methods

RL Course by David Silver - Lecture 5: Model Free Control

RL Course by David Silver - Lecture 9: Exploration and Exploitation

Virtual HLF 2020 – Talk: David Silver

RL Course by David Silver - Lecture 8: Integrating Learning and Planning

ICLR2015-david-silver-part1

Deep Reinforcement Learning with Subgoals - David Silver, NIPS 2017

RL Course by David Silver - Lecture 10: Classic Games

David Silver - The Nature of Randomization in Artificial Intelligence

David Silver - Deep Reinforcement Learning from AlphaGo to AlphaStar (Talk back at UAlberta) Part 1

Reinforcement Learning 10: Classic Games Case Study

RL Course by David Silver - Lecture 6: Value Function Approximation

David Silver - Deep Reinforcement Learning from AlphaGo to AlphaStar (Talk back at UAlberta) Q&A

RL Course by David Silver - Lecture 10: Classic Games [w/visible slides]

David Silver - Deep Reinforcement Learning from AlphaGo to AlphaStar (Talk back at UAlberta) Part 2

David Silver - Deep Reinforcement Learning from AlphaGo to AlphaStar (Talk back at UAlberta) Part 3

David Silver: Simulation-Based Search