Data

Tools

Indexes

Applications

Experiments

Open Source Science

297-value-evolutionary-based-reinforcement-learning

https://github.com/szu-advtech-2024/297-value-evolutionary-based-reinforcement-learning

Science Score: 31.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (4.8%) to scientific vocabulary
Last synced: 9 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: SZU-AdvTech-2024
  • Default Branch: main
  • Size: 0 Bytes
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Citation

https://github.com/SZU-AdvTech-2024/297-Value-Evolutionary-Based-Reinforcement-Learning/blob/main/ 

## Overview

VEB-RL is a hybrid framework designed for value-based reinforcement learning methods. It integrates genetic algorithms (GA) and cross-entropy method (CEM) to enhance the learning process using TD error as a fitness metric for more accurate value function approximation. The Elite Interaction Mechanism is also proposed to improve sample quality, significantly enhancing the performance of value-based RL across various tasks.

## Code

The code for VEB-RL is available on GitHub. You can access it at:
[https://github.com/yeshenpy/VEB-RL](https://github.com/yeshenpy/VEB-RL)

Owner

  • Name: SZU-AdvTech-2024
  • Login: SZU-AdvTech-2024
  • Kind: organization

Citation (citation.txt) 

@inproceedings{REPO297,
    author = "Li, Pengyi and Jianye, HAO and Tang, Hongyao and Zheng, Yan and Barez, Fazl",
    booktitle = "Forty-first International Conference on Machine Learning",
    title = "{Value-Evolutionary-Based Reinforcement Learning}",
    year = "2023"
}

GitHub Events

Total
  • Push event: 2
  • Create event: 3
Last Year
  • Push event: 2
  • Create event: 3