Fig. 1 (IMAGE)

Higher Education Press

Fig. 1

Caption

Comparison between clustering-based bonus rewards with novelty alone (η = 1.0) and clustering-based bonus rewards (η = 0.5). Here, the collected states (blue dots) are clustered into 5 clusters and the agent is rewarded with 1 in the orange area and receives no reward in other areas.

Credit

Xiao MA, Shen-Yi ZHAO, Zhao-Heng YIN, Wu-Jun LI

Usage Restrictions

none

License

Original content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.