Skip to content

Conversation

@lihuoran
Copy link
Contributor

Description

Update parallel RL. Now, MARO RL has full ability to run rollout & training under parallel mode.

  • Refine EnvSampler
    • Do not explicitly pass info_list. Instead, store info_list in the EnvSampler.
    • Add merge_metrics() to support metrics aggregation in parallel rollout.
    • Add EnvSamplerInterface as the base interface for EnvSampler and BatchEnvSampler.
    • Complete other previously missing features.
  • Trainer
    • Complete functions for parallel training (@remote functions).
  • MISCs
    • Add parallel RL configs for GYM tasks.
    • Fix several minor bugs.

Linked issue(s)/Pull request(s)

Type of Change

  • Non-breaking bug fix
  • Breaking bug fix
  • New feature
  • Test
  • Doc update
  • Docker update

Related Component

  • Simulation toolkit
  • RL toolkit
  • Distributed toolkit

Has Been Tested

  • OS:
    • Windows
    • Mac OS
    • Linux
  • Python version:
    • 3.7
    • 3.8
    • 3.9
  • Key information snapshot(s):

Needs Follow Up Actions

  • New release package
  • New docker image

Checklist

  • Add/update the related comments
  • Add/update the related tests
  • Add/update the related documentations
  • Update the dependent downstream modules usage

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants