DeepAI AI Chat
Log In Sign Up

Continual Learning from Demonstration of Robotic Skills

by   Sayantan Auddy, et al.

Methods for teaching motion skills to robots focus on training for a single skill at a time. Robots capable of learning from demonstration can considerably benefit from the added ability to learn new movements without forgetting past knowledge. To this end, we propose an approach for continual learning from demonstration using hypernetworks and neural ordinary differential equation solvers. We empirically demonstrate the effectiveness of our approach in remembering long sequences of trajectory learning tasks without the need to store any data from past demonstrations. Our results show that hypernetworks outperform other state-of-the-art regularization-based continual learning approaches for learning from demonstration. In our experiments, we use the popular LASA trajectory benchmark, and a new dataset of kinesthetic demonstrations that we introduce in this paper called the HelloWorld dataset. We evaluate our approach using both trajectory error metrics and continual learning metrics, and we propose two new continual learning metrics. Our code, along with the newly collected dataset, is available at


page 1

page 5

page 7


Don't forget, there is more than forgetting: new metrics for Continual Learning

Continual learning consists of algorithms that learn from a stream of da...

Batch-level Experience Replay with Review for Continual Learning

Continual learning is a branch of deep learning that seeks to strike a b...

A Scalable Approach to Multi-Context Continual Learning via Lifelong Skill Encoding

Continual or lifelong learning (CL) is one of the most challenging probl...

A Simple Approach to Continual Learning by Transferring Skill Parameters

In order to be effective general purpose machines in real world environm...

Continual Learning for Text Classification with Information Disentanglement Based Regularization

Continual learning has become increasingly important as it enables NLP m...

TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models

Language Models (LMs) become outdated as the world changes; they often f...

Continual Learning Augmented Investment Decisions

Investment decisions can benefit from incorporating an accumulated knowl...

Code Repositories


Code for the paper Continual Learning from Demonstration of Robotic Skills

view repo