Deep Kernels for Optimizing Locomotion Controllers
Sample efficiency is important when optimizing parameters of locomotion controllers, since hardware experiments are time consuming and expensive. Bayesian Optimization, a sample-efficient optimization framework, has recently been widely applied to address this problem, but further improvements in sample efficiency are needed for practical applicability to real-world robots and high-dimensional controllers. To address this, prior work has proposed using domain expertise for constructing custom distance metrics for locomotion. In this work we show how to learn such a distance metric automatically. We use a neural network to learn an informed distance metric from data obtained in high-fidelity simulations. We conduct experiments on two different controllers and robot architectures. First, we demonstrate improvement in sample efficiency when optimizing a 5-dimensional controller on the ATRIAS robot hardware. We then conduct simulation experiments to optimize a 16-dimensional controller for a 7-link robot model and obtain significant improvements even when optimizing in perturbed environments. This demonstrates that our approach is able to enhance sample efficiency for two different controllers, hence is a fitting candidate for further experiments on hardware in the future.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian OptimizationSimilar Papers 제목 키워드 기반
Learning to Exploit Elastic Actuators for Quadruped Locomotion
Spring-based actuators in legged locomotion provide energy-efficiency and improved performance, but increase the difficulty of controller design. While previous work has focused on extensive modeling and simulation to fi…
Sample Efficient Optimization for Learning Controllers for Bipedal Locomotion
Learning policies for bipedal locomotion can be difficult, as experiments are expensive and simulation does not usually transfer well to hardware. To counter this, we need al- gorithms that are sample efficient and inher…
Bayesian OptimizationImplementation of Fuzzy Control Algorithm in Two-Wheeled Differential Drive Platform
Designing and developing Artificial Intelligence controllers on separately dedicated chips have many advantages. This report reviews the development of a real-time fuzzy logic controller for optimizing locomotion control…
Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers
Legged locomotion has recently achieved remarkable success with the progress of machine learning techniques, especially deep reinforcement learning (RL). Controllers employing neural networks have demonstrated empirical …
Deep Reinforcement LearningReinforcement Learning (RL)Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots
Developing robust walking controllers for bipedal robots is a challenging endeavor. Traditional model-based locomotion controllers require simplifying assumptions and careful modelling; any small errors can result in uns…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)