Automated Curriculum Learning for Embodied Agents: A Neuroevolutionary Approach

by   Nicola Milano, et al.

We demonstrate how an evolutionary algorithm can be extended with a curriculum learning process that selects automatically the environmental conditions in which the evolving agents are evaluated. The environmental conditions are selected so to adjust the level of difficulty to the ability level of the current evolving agents and so to challenge the weaknesses of the evolving agents. The method does not require domain knowledge and does not introduce additional hyperparameters. The results collected on two benchmark problems, that require to solve a task in significantly varying environmental conditions, demonstrate that the method proposed outperforms conventional algorithms and generates solutions that are robust to variations


page 4

page 10

page 13


The Role of Environmental Variations in Evolutionary Robotics: Maximizing Performance and Robustness

Exposing evolving robots to variable conditions is necessary to obtain s...

Robust Optimization through Neuroevolution

We propose a method for evolving solutions that are robust with respect ...

Moderate Environmental Variation Promotes Adaptation in Artificial Evolution

In this paper we analyze the role of environmental variations in the evo...

Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions

While the history of machine learning so far encompasses a series of pro...

Curriculum Manager for Source Selection in Multi-Source Domain Adaptation

The performance of Multi-Source Unsupervised Domain Adaptation depends s...

A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances

In recent years, we have witnessed tremendous progress in deep reinforce...