# Autonomous Open-Ended Learning of Interdependent Tasks

## TL;DR

This paper introduces an autonomous learning architecture for robots that manages interdependent tasks by framing task selection as a Markov Decision Process, enabling the robot to learn multiple interconnected skills in a fully autonomous manner.

## Contribution

It presents a novel decision-making framework for autonomous open-ended learning of interdependent tasks, extending intrinsic motivation approaches to hierarchical and interdependent scenarios.

## Key findings

- Successfully applied to a humanoid robot for interdependent reaching tasks
- Demonstrated improved competence across multiple interconnected skills
- Showed potential for scalable autonomous skill acquisition

## Abstract

Autonomy is fundamental for artificial agents acting in complex real-world scenarios. The acquisition of many different skills is pivotal to foster versatile autonomous behaviour and thus a main objective for robotics and machine learning. Intrinsic motivations have proven to properly generate a task-agnostic signal to drive the autonomous acquisition of multiple policies in settings requiring the learning of multiple tasks. However, in real world scenarios tasks may be interdependent so that some of them may constitute the precondition for learning other ones. Despite different strategies have been used to tackle the acquisition of interdependent/hierarchical tasks, fully autonomous open-ended learning in these scenarios is still an open question. Building on previous research within the framework of intrinsically-motivated open-ended learning, we propose an architecture for robot control that tackles this problem from the point of view of decision making, i.e. treating the selection of tasks as a Markov Decision Process where the system selects the policies to be trained in order to maximise its competence over all the tasks. The system is then tested with a humanoid robot solving interdependent multiple reaching tasks.