Towards Deep Robot Learning with Optimizer applicable to Non-stationary Problems

07/31/2020
by   Taisuke Kobayashi, et al.
0

This paper proposes a new optimizer for deep learning, named d-AmsGrad. In the real-world data, noise and outliers cannot be excluded from dataset to be used for learning robot skills. This problem is especially striking for robots that learn by collecting data in real time, which cannot be sorted manually. Several noise-robust optimizers have therefore been developed to resolve this problem, and one of them, named AmsGrad, which is a variant of Adam optimizer, has a proof of its convergence. However, in practice, it does not improve learning performance in robotics scenarios. This reason is hypothesized that most of robot learning problems are non-stationary, but AmsGrad assumes the maximum second momentum during learning to be stationarily given. In order to adapt to the non-stationary problems, an improved version, which slowly decays the maximum second momentum, is proposed. The proposed optimizer has the same capability of reaching the global optimum as baselines, and its performance outperformed that of the baselines in robotics problems.

READ FULL TEXT

page 1

page 4

research
05/28/2022

Non-stationary Transformers: Rethinking the Stationarity in Time Series Forecasting

Transformers have shown great power in time series forecasting due to th...
research
05/21/2018

Non-Oscillatory Pattern Learning for Non-Stationary Signals

This paper proposes a novel non-oscillatory pattern (NOP) learning schem...
research
07/30/2023

Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup

Adaptive optimization has achieved notable success for distributed learn...
research
07/25/2023

A behavioural transformer for effective collaboration between a robot and a non-stationary human

A key challenge in human-robot collaboration is the non-stationarity cre...
research
02/29/2020

TAdam: A Robust Stochastic Gradient Optimizer

Machine learning algorithms aim to find patterns from observations, whic...
research
04/13/2022

LDPC codes: tracking non-stationary channel noise using sequential variational Bayesian estimates

We present a sequential Bayesian learning method for tracking non-statio...
research
09/05/2023

Learning Observation Models with Incremental Non-Differentiable Graph Optimizers in the Loop for Robotics State Estimation

We consider the problem of learning observation models for robot state e...

Please sign up or login with your details

Forgot password? Click here to reset