Skip to content
GitLab
Projects Groups Snippets
  • /
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
    • Contribute to GitLab
  • Sign in / Register
  • M Mario-Level-1
  • Project information
    • Project information
    • Activity
    • Labels
    • Members
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributors
    • Graph
    • Compare
  • Issues 20
    • Issues 20
    • List
    • Boards
    • Service Desk
    • Milestones
  • Merge requests 7
    • Merge requests 7
  • CI/CD
    • CI/CD
    • Pipelines
    • Jobs
    • Schedules
  • Deployments
    • Deployments
    • Environments
    • Releases
  • Packages and registries
    • Packages and registries
    • Package Registry
    • Infrastructure Registry
  • Monitor
    • Monitor
    • Incidents
  • Analytics
    • Analytics
    • Value stream
    • CI/CD
    • Repository
  • Wiki
    • Wiki
  • Snippets
    • Snippets
  • Activity
  • Graph
  • Create a new issue
  • Jobs
  • Commits
  • Issue Boards
Collapse sidebar
  • Justin Armstrong
  • Mario-Level-1
  • Issues
  • #27
Closed
Open
Issue created Nov 06, 2017 by Ja1r0@Ja1r0

How to hold on the game waitting the trainning of an agent

I am trying to use this game environment to train an agent by learning algorithm.But each trainning step need much time,so that the game enviroment can't recieve an action without delay.Actually the game will stack at one frame due to the delay of the action command.How should I pause the game and train my agent,and start it again when the train step is over?I am struggling for this issue for a long time.

Assignee
Assign to
Time tracking