Influence-Based Abstraction in Deep Reinforcement Learning

We have some first results on using influence-based abstractions in the context of deep reinforcement learning, which will be presented at the ALA workshop in Montreal.

See the paper here or have a look at some of the videos.


Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes:

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>