Neural fidelity warping for efficient robot morphology design
arXiv:2012.04195
Abstract
We consider the problem of optimizing a robot morphology to achieve the best performance for a target task, under computational resource limitations. The evaluation process for each morphological design involves learning a controller for the design, which can consume substantial time and computational resources. To address the challenge of expensive robot morphology evaluation, we present a continuous multi-fidelity Bayesian Optimization framework that efficiently utilizes computational resources via low-fidelity evaluations. We identify the problem of non-stationarity over fidelity space. Our proposed fidelity warping mechanism can learn representations of learning epochs and tasks to model non-stationary covariances between continuous fidelity evaluations which prove challenging for off-the-shelf stationary kernels. Various experiments demonstrate that our method can utilize the low-fidelity evaluations to efficiently search for the optimal robot morphology, outperforming state-of-the-art methods.
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Predictive Entropy Search for Efficient Global Optimization of Black-box Functions
- Input Warping for Bayesian Optimization of Non-stationary Functions
- A General Framework for Multi-fidelity Bayesian Optimization with Gaussian Processes
- Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
- Bayesian Optimization with Adaptive Kernels for Robot Control
- Neural Graph Evolution: Towards Efficient Automatic Robot Design
- Heteroscedastic Treed Bayesian Optimisation
- Multi-fidelity Bayesian Optimization with Max-value Entropy Search and its parallelization