Manifold Blog

Manifold Blog

Rajendra Koppula

Rajendra Koppula
Find me on:

Recent Posts

Exploration vs. Exploitation in Reinforcement Learning

Posted by Rajendra Koppula on Jan 8, 2019 7:00:00 AM

Introduction

The last five years have seen many new developments in reinforcement learning (RL), a very interesting sub-field of machine learning (ML). Publication of "Deep Q-Networks" from DeepMind, in particular, ushered in a new era. As RL comes into its own, it's becoming clear that a key concept in all RL algorithms is the tradeoff between exploration and exploitation. In this post, we will simulate a problem called the "multi-armed bandit" in order to understand the details of this tradeoff. 

Read More

Topics: Machine learning

Never Miss a Post

Get the Manifold Blog in Your Inbox

We publish occasional blog posts about our client work, open source projects, and conference experiences. We focus on industry insights and practical takeaways to help you accelerate your data roadmap and create business value.


Subscribe Here


Recent Posts