Skip to content

Adapting to Continuous Action Spaces #8

@zulfiqar-zaidi

Description

@zulfiqar-zaidi

Hi,

Do you think the algorithm can be easily adapted to environments with continuous action space. If so, what changes do you think are required. One of the things that I think that need to be converted is the summation term in the denominator of eq. 11 of the paper (https://arxiv.org/pdf/2102.06483.pdf). Do you have any ideas/pointers on how to achieve it? Additionally, will it require any other modification than the one above for adapting it to continuous action spaces.

Thank you!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions