May 30, 2024

[ad_1]

By simple color-masking, high-level image statistics can be derived. Rewarding an agent for deliberately changing these statistics, leads to diverse exploration and interesting behavior like, for example, grasping or lifting objects.

Example Skills

Learned from scratch and from pixels and proprioception only. The external rewards are sparse and Simple Sensor Intentions (SSIs) are used as the only auxiliary tasks.

Video

[ad_2]

Source link

Leave a Reply

Your email address will not be published. Required fields are marked *