Teaching Curiosity-Driven AI to Play Games
Subscribe:  iCal  |  Google Calendar
1, Jul — 1, Aug
Cambridge GB   13, Jul — 17, Jul
San Diego US   19, Jul — 23, Jul
Torino IT   25, Jul — 29, Jul
Shanghai CN   3, Aug — 7, Aug
Latest comments
by Lewis Cowles
4 hours ago

Looks amazing

by aakashmishra0709@gmail.com
6 hours ago

Hey now you can easily recover your settings and data from your previous version of windows just visit our website and get the tutorial by which you will learn the process to continue outlook sync settings windows 10 operating system with the help of pictures in easy steps without any interruption.

by aakashmishra0709@gmail.com
6 hours ago

Hey thanks for this article, I have one of the most popular game to play just visit our website and play free spades online game on our homepage without any payment and without any app installation.

Teaching Curiosity-Driven AI to Play Games
25 June, 2018

Take a look at another work that explains a way we can use AI to play games. The thing is that this one focuses on curiosity. How can a machine be curious? In this case, curiosity is defined by the AI’s ability to predict the results of its own actions. And this is big because the AI has the tools to acquire skills that don’t seem necessary now but might be in the future. 

First, let’s start by check it out a video on the paper by Two Minute Papers:


In many real-world scenarios, rewards extrinsic to the agent are extremely sparse or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent to explore its environment and learn skills that might be useful later in its life. We formulate curiosity as the error in an agent’s ability to predict the consequence of its own actions in a visual feature space learned by a self-supervised inverse dynamics model. Our formulation scales to high-dimensional continuous state spaces, like images, bypasses the difficulties of directly predicting pixels, and, critically, ignores the aspects of the environment that cannot affect the agent. The proposed approach is evaluated in two environments: VizDoomand Super Mario Bros. Three broad settings are investigated: 1) sparse extrinsic reward, where curiosity allows for far fewer interactions with the environment to reach the goal; 2) exploration with no extrinsic reward, where curiosity pushes the agent to explore more efficiently; and 3) generalization to unseen scenarios (e.g. new levels of the same game) where the knowledge gained from earlier experience helps the agent explore new places much faster than starting from scratch. 

The paper “Curiosity-driven Exploration by Self-supervised Prediction” and its source code can be found here.

Leave a Reply

Be the First to Comment!