Self-Supervised Exploration via Disagreement

Dhiraj Gandhi
Dhiraj Gandhi

International Conference on Machine Learning, pp. 5062-5071, 2019.

Cited by: 67|Views49
EI
Weibo:
Instead of learning a single dynamics model, we propose an alternate exploration formulation based on ensemble of models as inspired by the classical active learning literature

Abstract:

Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and simulation. However, most of these formulations either get stuck in environments with stochastic dynamics or are too inefficient to be scalable to real robotics se...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments