Russell Mendonca
Description: ALAN : Autonomously Exploring Robotic Agents in the Real World
machine learning (3372) exploration (796) unsupervised learning (10) world models (7)
Robotic agents that operate autonomously in the real world need to continuously explore their environment and learn from the data collected, with minimal human supervision. While it is possible to build agents that can learn in such a manner without supervision, current methods struggle to scale to the real world. Thus, we propose ALAN, an autonomously exploring robotic agent, that can perform many tasks in the real world with little training and interaction time. This is enabled by measuring environment ch
After autonomous exploration the robot can perform tasks involving multiple objects in a zero-shot manner using goal reaching.
An example of the binary change image extracted from a pair of images, which detects pixels where change has occured.
Russell Mendonca