paper-with-me

Papers

Adaptive t-Momentum-based Optimization for Unknown Ratio of Outliers in Amateur Data in Imitation Learning

2021-08-02 · Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Kenji Sugimoto

Behavioral cloning (BC) bears a high potential for safe and direct transfer of human skills to robots. However, demonstrations performed by human operators often contain noise or imperfect behaviors that can affect the efficiency of the imitator if left unchecked. In order to allow the imitators to effectively learn from imperfect demonstrations, we propose to employ the robust t-momentum optimization algorithm. This algorithm builds on the Student's t-distribution in order to deal with heavy-tailed data and reduce the effect of outlying observations. We extend the t-momentum algorithm to allow for an adaptive and automatic robustness and show empirically how the algorithm can be used to produce robust BC imitators against datasets with unknown heaviness. Indeed, the imitators trained with the t-momentum-based Adam optimizers displayed robustness to imperfect demonstrations on two different manipulation tasks with different robots and revealed the capability to take advantage of the additional data while reducing the adverse effect of non-optimal behaviors.

📄 PDF Abstract BibTeX arXiv:2108.00625

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation Learning

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Similar Papers 제목 키워드 기반

Adaptive Optimization via Momentum on Variance-Normalized Gradients

2026-02-10 · Francisco Patitucci, Aryan Mokhtari arxiv

We introduce MVN-Grad (Momentum on Variance-Normalized Gradients), an Adam-style optimizer that improves stability and performance by combining two complementary ideas: variance-based normalization and momentum applied a…

Image Classification

Optimal Adaptive and Accelerated Stochastic Gradient Descent

2018-10-01 · Qi Deng, Yi Cheng, Guanghui Lan

Stochastic gradient descent (\textsc{Sgd}) methods are the most powerful optimization tools in training machine learning and deep learning models. Moreover, acceleration (a.k.a. momentum) methods and diagonal scaling (a.…

BIG-bench Machine LearningStochastic Optimization

Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization

2021-10-18 · Tao Sun, Huaming Ling, Zuoqiang Shi, Dongsheng Li 외

Heavy ball momentum is crucial in accelerating (stochastic) gradient-based optimization algorithms for machine learning. Existing heavy ball momentum is usually weighted by a uniform hyperparameter, which relies on exces…

BIG-bench Machine Learningimage-classificationImage ClassificationLanguage Modeling+3

Stochastic Gradient Descent with Nonlinear Conjugate Gradient-Style Adaptive Momentum

2020-12-03 · Bao Wang, Qiang Ye

Momentum plays a crucial role in stochastic gradient-based optimization algorithms for accelerating or improving training deep neural networks (DNNs). In deep learning practice, the momentum is usually weighted by a well…

Adversarial Robustness

Adaptive Momentum Coefficient for Neural Network Optimization

2020-06-04 · Zana Rashidi, Kasra Ahmadi K. A., Aijun An, Xiaogang Wang

We propose a novel and efficient momentum-based first-order algorithm for optimizing neural networks which uses an adaptive coefficient for the momentum term. Our algorithm, called Adaptive Momentum Coefficient (AMoC), u…