Evolving generalist controllers to handle a wide range of morphological variations
Neuro-evolutionary methods have proven effective in addressing a wide range of tasks. However, the study of the robustness and generalizability of evolved artificial neural networks (ANNs) has remained limited. This has immense implications in the fields like robotics where such controllers are used in control tasks. Unexpected morphological or environmental changes during operation can risk failure if the ANN controllers are unable to handle these changes. This paper proposes an algorithm that aims to enhance the robustness and generalizability of the controllers. This is achieved by introducing morphological variations during the evolutionary training process. As a results, it is possible to discover generalist controllers that can handle a wide range of morphological variations sufficiently without the need of the information regarding their morphologies or adaptation of their parameters. We perform an extensive experimental analysis on simulation that demonstrates the trade-off between specialist and generalist controllers. The results show that generalists are able to control a range of morphological variations with a cost of underperforming on a specific morphology relative to a specialist. This research contributes to the field by addressing the limited understanding of robustness and generalizability and proposes a method by which to improve these properties.
Code (2)
Similar Papers 제목 키워드 기반
GeCCo -- a Generalist Contact-Conditioned Policy for Loco-Manipulation Skills on Legged Robots
Most modern approaches to quadruped locomotion focus on using Deep Reinforcement Learning (DRL) to learn policies from scratch, in an end-to-end manner. Such methods often fail to scale, as every new problem or applicati…
Reinforcement LearningThe Evaluation Cost of Task Specialization in Evolutionary Multi-Robot Systems
Task specialization can improve the efficiency of multi-robot systems (MRSs). Previous works have investigated the emergence of task-specialist robot controllers through evolutionary optimization and have argued that tas…
On the Cost of Evolving Task Specialization in Multi-Robot Systems
Task specialization can lead to simpler robot behaviors and higher efficiency in multi-robot systems. Previous works have shown the emergence of task specialization during evolutionary optimization, focusing on feasibili…
Octo: An Open-Source Generalist Robot Policy
Large policies pretrained on diverse robot datasets have the potential to transform robotic learning: instead of training new policies from scratch, such generalist robot policies may be finetuned with only a little in-d…
Robot ManipulationGOAL: A Generalist Combinatorial Optimization Agent Learning
Machine Learning-based heuristics have recently shown impressive performance in solving a variety of hard combinatorial optimization problems (COPs). However they generally rely on a separate neural model, specialized an…
Combinatorial OptimizationSchedulingTransfer Learning