Name: Human-level control through deep reinforcement learning
Start: 2018-02-19T19:00:00-06:00
End: 2018-02-19T21:00:00-06:00
Location: Human Spaces

The Paper:
https://web.stanford.edu/class/psych209/Readings/MnihEtAlHassibis15NatureControlDeepRL.pdf

The Hook:
If you’re someone like me who regularly attends the local Papers We Love meetup, then you’ve probably heard something about the latest breakthroughs in reinforcement learning such as:

Where a bipedal agent learns to not only walk with a simple reward function, but also navigate obstacles:

https://arxiv.org/abs/1707.02286
https://www.youtube.com/watch?v=hx_bgoTF7bs

Where an agent learns to play go with no human teaching, simply by playing itself:

https://deepmind.com/blog/alphago-zero-learning-scratch/

The Talk:
These breakthroughs are the result of advancements in Deep RL, and one of the seminal papers on this subject is Mnih et al 2015. This is the paper discussing the work done at Google Deep Mind to learn how to play various Atari games by only using the pixels on the screen as input, and the game score as the reward function.

Before we dive into all the shiny new gadgetry, we’ll look at a bit of the fundamental math and history in RL including the Bellman Equation, and some fundamental algorithms such as policy iteration, value iteration, and q-learning.

We will also be talking about the OpenAI Gym framework. This Python framework contains many RL problems allowing you to easily test your algorithms against several problems.

https://github.com/openai/gym

There will be food sponsored by Slalom consulting.

Mark

Papers We Love (Saint Louis Chapter)

Technology

Artificial Intelligence

Statistical Computing

Computer Programming

Programming Languages

Computer Science

High Scalability Computing

Machine Learning

High Performance Computing

Computational Science and Engineering

Human-level control through deep reinforcement learning

Human Spaces

Share

Papers We Love (Saint Louis Chapter)

Human-level control through deep reinforcement learning

Papers We Love (Saint Louis Chapter)

Details

Members are also interested in