Skip to main navigation Skip to search Skip to main content

Hindsight Balanced Reward Shaping

  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Sparse rewards is a tricky problem in reinforcement learning and reward shaping is commonly used to solve the problem of sparse rewards in specific tasks, but it often requires priori knowledge and manually designing rewards, which are costly in many cases. Hindsight experience replay (HER) solves the problem of sparse rewards in multi-goal scenarios by replacing the goal of a failed trajectory with a virtual goal. Our method integrates the ideas of reward shaping and HER, which has two advantages: First, it can automatically perform reward shaping without manually-designed reward functions; Second, it can solve the problem arising from the use of virtual goals in HER. Experiment results show our method can significantly improve the performance in both Bit-Flipping environment and Mujoco environment.

Original languageEnglish
Title of host publicationNeural Information Processing - 29th International Conference, ICONIP 2022, Proceedings
EditorsMohammad Tanveer, Sonali Agarwal, Seiichi Ozawa, Asif Ekbal, Adam Jatowt
PublisherSpringer Science and Business Media Deutschland GmbH
Pages492-503
Number of pages12
ISBN (Print)9789819916412
DOIs
StatePublished - 2023
Event29th International Conference on Neural Information Processing, ICONIP 2022 - Virtual, Online, India
Duration: 22 Nov 202226 Nov 2022

Publication series

NameCommunications in Computer and Information Science
Volume1792 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference29th International Conference on Neural Information Processing, ICONIP 2022
Country/TerritoryIndia
CityVirtual, Online
Period22/11/2226/11/22

Keywords

  • hindsight experience replay
  • reinforcement learning
  • reward shaping
  • sparse reward

Fingerprint

Dive into the research topics of 'Hindsight Balanced Reward Shaping'. Together they form a unique fingerprint.

Cite this