No recording or live stream video available yet.

Please check back a few days before the event starts.

Object-Level Self-Supervised Learning to Speed-Up Reinforcement Learning in Visual and Text Environments

Time: Wednesday 30-Sept-2020 16:00
Live in 11 days & 01:08:41


Artifacts

Motivation / Abstract
Pascal will present two techniques to automatically infer high-level object information from low-level pixel intensities and raw text to accelerate the optimization of a good policy in deep reinforcement learning.

The first approach, called MOREL (Motion Oriented REinforcement Learning), consists of a self-supervised technique that learns to detect moving objects in video games. The second approach also consists of a self-supervised technique that automatically infers a belief graph of objects and relations described in text.

These techniques allow RL agents to reason at a high level and therefore need less interaction with the environment to find good policies. Furthermore, we can gain insights and some degree of explainability into the resulting policies by inspecting the objects they depend on. The techniques will be demonstrated in Atari Games and TextWorld.
Stream Categories:
 Reinforcement Learning

Join This Event

Live chat will be available close to event start date.


View All Upcoming Events
Code of ConductTerms and Conditions