Neural Dynamic Policies for End-to-End Sensorimotor Learning

Shikhar Bahl
Shikhar Bahl
Mustafa Mukadam
Mustafa Mukadam

NIPS 2020, 2020.

Cited by: 0|Views27
EI
Weibo:
We propose a novel re-parameterization of action spaces via Neural Dynamic Policies, a set of policies which impose the structure of a dynamical system on action spaces

Abstract:

The current dominant paradigm in sensorimotor control, whether imitation or reinforcement learning, is to train policies directly in raw action spaces such as torque, joint angle, or end-effector position. This forces the agent to make decisions individually at each timestep in training, and hence, limits the scalability to continuous, ...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments