Curiosity-driven Exploration by Self-supervised Prediction

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 488-489, 2017.

Cited by: 991|Views231
EI
Weibo:
We provide the prediction error of the forward dynamics model to the agent as an intrinsic reward to encourage its curiosity

Abstract:

In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent to explore its environment and learn skills that might be useful later in its life. We formulate curiosity as the error in an agentu0027s ability to p...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments