Stanford Reinforcement Learning – Lecture 2 – Given a Model of the World

Stanford Reinforcement Learning – Lecture 2 – Given a Model of the World

Professor Emma Brunskill of Stanford University talks covers the fundamentals of reinforcement learning in this second lecture of the course “Reinforcement Learning Winter 2019.” (The... Details
Greg Brockman on OpenAI and AGI

Greg Brockman on OpenAI and AGI

In this video, Lex Fridman interviews Greg Brockman, Co-Founder and CTO of OpenAI. OpenAI is a research organization developing ideas in AI that lead eventually... Details
Reinforcement Learning Lecture from Stanford

Reinforcement Learning Lecture from Stanford

Professor Emma Brunskill of Stanford University talks covers the fundamentals of reinforcement learning in this first lecture of the course “Reinforcement Learning Winter 2019.” Details
Reinforcement Learning in TensorFlow with TF-Agents

Reinforcement Learning in TensorFlow with TF-Agents

In this video from TF Dev Summit 2019, learn how to use TensorFlow and Reinforcement Learning to solve complex tasks. Details
DeepMind StarCraft

DeepMind StarCraft

In this video, Siraj Raval explores the work behind the creation of DeepMind’s AlphaStar, which pushes AI to the next level. Details
AI Learns to DRIVE

AI Learns to DRIVE

Code Bullet experiments with a brand new (form him) algorithm, QLearning, and teaches an AI how to drive. Details
DeepMind’s AlphaStar Beats Humans 10-0

DeepMind’s AlphaStar Beats Humans 10-0

In this video, Two Minute Papers explores DeepMind’s AlphaStar. Details
Spinning Up in Deep RL Workshop

Spinning Up in Deep RL Workshop

In this video, Joshua Achiam explores reinforcement learning and exploring the OpenAI environment. Details
Introduction to Deep Reinforcement Learning

Introduction to Deep Reinforcement Learning

Lex Fridman has just posted this video of the first lecture of MIT course 6.S091: Deep Reinforcement Learning, introducing the fascinating field of Deep RL.... Details
An AI that Can Learn from Humans (and then Exceed Them)

An AI that Can Learn from Humans (and then Exceed Them)

Two Minute Papers has a video on a recently published paper about an AI that learns from observing humans and what makes this approach different... Details