Tags » Reinforcement Learning

5 easy pieces: How Deepmind mastered Go

Google Deepmind announced last week that it created an AI that can play professional-level Go. The game of Go has always been something of a holy grail for game AI, given its large branching factor and the difficulty of evaluating a position. 1,741 more words

Journal Club

Play Your Cards Right with Python

Peters, my morbidly objectionable Dutch lodger, has won every game of cards against me. He now owns the deeds to my house, the yellow car on the driveway and even the clothes on my back (if the fat fool could squeeze into them, that is). 655 more words

Technology

Useful Control Variates for Variance Reduction

Motivation

For many problems in machine learning (ranging from Generative Models to Reinforcement Learning), we rely on Monte Carlo estimators of gradients for optimization. Often, the… 129 more words

Expectations

NIPS 2015 - Deep RL Workshop

This is a brief summary of the first part of the Deep RL workshop at NIPS 2015. I couldn’t get a seat for the second half… 1,198 more words

Research

Deep Reinforcement Learning with Double Q-learning

We recently published a paper on deep reinforcement learning with Double Q-learning, demonstrating that Q-learning learns overoptimistic action values when combined with deep neural networks, even on deterministic environments such as Atari video games, and that this can be remedied by using a variant of… 153 more words

Paper

NIPS 2015 - RL Tutorial

Rich Sutton gave a tutorial on function approximation in RL. Rich being one of the pioneers of RL, I was looking forward to his insights. He started off with some… 1,013 more words

Conferences