Generalization in Deep Reinforcement Learning for Robotic Navigation by Reward Shaping-Reference-Cited by-同舟云学术

Generalization in Deep Reinforcement Learning for Robotic Navigation by Reward Shaping

Published:2024-06 Issue:6 Volume:71 Page:6013-6020
ISSN:0278-0046
Container-title:IEEE Transactions on Industrial Electronics
language:
Short-container-title:IEEE Trans. Ind. Electron.

Author:

Miranda Victor R. F.¹^ORCID,Neto Armando A.¹^ORCID,Freitas Gustavo M.¹^ORCID,Mozelli Leonardo A.¹^ORCID

Affiliation:

1. Graduate Program in Electrical Engineering (PPGEE), Department of Electronics Engineering (DELT), Department of Electrical Engineering (DEE), Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil

Funder

CAPES - Finance Code 001

Conselho Nacional de Desenvolvimento Científico e Tecnológico

Fundação de Amparo à Pesquisa do Estado de Minas Gerais

NVIDIA

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Control and Systems Engineering

Link

http://xplorestaging.ieee.org/ielx7/41/10416960/10173760.pdf?arnumber=10173760

Reference37 articles.

1. Human-level control through deep reinforcement learning

2. A survey on Image Data Augmentation for Deep Learning

3. Domain randomization for transferring deep neural networks from simulation to the real world

4. Sim-to-Real Transfer of Robotic Control with Dynamics Randomization

5. Improving generalization in reinforcement learning with mixture regularization;Wang,2020

Cited by 4 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Deep reinforcement learning based mapless navigation for industrial AMRs: advancements in generalization via potential risk state augmentation;Applied Intelligence;2024-07-13

2. A zero-shot reinforcement learning strategy for autonomous guidewire navigation;International Journal of Computer Assisted Radiology and Surgery;2024-04-16

3. Continuous Decision-Making in Lane Changing and Overtaking Maneuvers for Unmanned Vehicles: A Risk-Aware Reinforcement Learning Approach With Task Decomposition;IEEE Transactions on Intelligent Vehicles;2024-04

4. The Impact of LiDAR Configuration on Goal-Based Navigation within a Deep Reinforcement Learning Framework;Sensors;2023-12-09