Deep Reinforcement Learning of Universal Policies with Diverse Environment Summaries

Felix Berkenkamp
Felix Berkenkamp

2018.

Cited by: 0|Bibtex|Views11

Abstract:

Deep reinforcement learning has enabled robots to complete complex tasks in simulation. However, the resulting policies do not transfer to real robots due to model errors in the simulator. One solution is to randomize the simulation environment, so that the resulting, trained policy achieves high performance in expectation over a variety ...More

Code:

Data:

Your rating :
0

 

Tags
Comments