Publication

Dynamic Experience Replay

This paper presents a novel technique in reinforcement learning that largely improves the training efficiency, especially in contact-rich robotic assembly tasks.

Download publication

Abstract

Dynamic Experience Replay

Jieliang Luo, Hui Li

Conference on Robot Learning 2019

We present a novel technique called Dynamic Experience Replay (DER) that allows Reinforcement Learning (RL) algorithms to use experience replay samples not only from human demonstrations but also successful transitions generated by RL agents during training and therefore improve training efficiency. It can be combined with an arbitrary off-policy RL algorithm, such as DDPG or DQN, and their distributed versions. We build upon Ape-X DDPG and demonstrate our approach on robotic tight-fitting joint assembly tasks, based on force/torque and Cartesian pose observations. In particular, we run experiments on two different tasks: peg-in-hole and lap-joint. In each case, we compare different replay buffer structures and how DER affects them. Our ablation studies show that Dynamic Experience Replay is a crucial ingredient that either largely shortens the training time in these challenging environments or solves the tasks that the vanilla Ape-X DDPG cannot solve. We also show that our policies learned purely in simulation can be deployed successfully on the real robot.

Related Resources

Publication

2021

Perception! Immersion! Empowerment! Superpowers as Inspiration for Visualization

We explore how the lens of fictional superpowers can help characterize…

Publication

1998

Compatibility and Interaction Style in Computer Graphics

Recent trends in human computer interaction have focused on…

Publication

2017

Nature-based Hybrid Computational Geometry System for Optimizing Component Structure

This paper describes a novel computational geometry system developed…

Publication

2018

Dream Lens: Exploration and Visualization of Large-Scale Generative Design Datasets

This paper presents Dream Lens, an interactive visual analysis tool…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us