Model-Based Action Exploration for Learning Dynamic Motion Skills

Alex Kyriazis
Alex Kyriazis
Ivan Zinin
Ivan Zinin
William Choi
William Choi

IROS, pp. 1540-1546, 2018.

Cited by: 2|Views24
EI

Abstract:

Deep reinforcement learning has achieved great strides in solving challenging motion control tasks. Recently, there has been significant work on methods for exploiting the data gathered during training, but there has been less work on how to best generate the data to learn from. For continuous action domains, the most common method for ge...More

Code:

Data:

Get fulltext within 24h
Bibtex
Your rating :
0

 

Tags
Comments