Contributed Talk 2: Emergent Communication With World Models

NeurIPS 2019

Contributed Talk 2: Emergent Communication With World Models

Dec 14, 2019
|
40 views
|
|
Code
Details
We explore building generative neural network models of popular reinforcement learning environments. Our world model can be trained quickly in an unsupervised manner to learn a compressed spatial and temporal representation of the environment. By using features extracted from the world model as inputs to an agent, we can train a very compact and simple policy that can solve the required task. We can even train our agent entirely inside of its own hallucinated dream generated by its world model, and transfer this policy back into the actual environment. An interactive version of this paper is available at https://worldmodels.github.io/ Speakers: Alexander I. Cowen-Rivers

Comments
loading...