Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feature(lisong): add sqil_sac example #374

Merged
merged 7 commits into from
Jun 27, 2022
Merged

Conversation

song2181
Copy link
Contributor

@song2181 song2181 commented Jun 15, 2022

Description

add sqil_sac example

Related Issue

fix bug in sqilsac policy

TODO

Check List

  • merge the latest version source branch/repo, and resolve all the conflicts
  • pass style check
  • pass all the tests

@PaParaZz1 PaParaZz1 added refactor refactor module or component labels Jun 16, 2022
ding/example/sqil_sac.py Outdated Show resolved Hide resolved
[main_config, create_config],
[expert_main_config, expert_create_config],
seed=0,
)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please add a new empty line at the end of the file.
Usually, it would not pass the format test.

Copy link
Collaborator

@zjowowen zjowowen left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This commit is a good implement of sqil-sac in new pipeline.
It would be better if expert model file be uploaded into a test folder so that we could run it directly, for most of the imitation learning algos.

ding/example/sqil_sac.py Outdated Show resolved Hide resolved
task.use(StepCollector(cfg, expert_policy.collect_mode, expert_collector_env)) # expert data collector
task.use(
StepCollector(
cfg, expert_policy.collect_mode, expert_collector_env, cfg.policy.get('expert_random_collect_size', 0)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

don't use xxx.get as much as possible

ding/example/sqil_sac.py Outdated Show resolved Hide resolved
@PaParaZz1 PaParaZz1 added enhancement New feature or request and removed refactor refactor module or component labels Jun 23, 2022
@PaParaZz1 PaParaZz1 merged commit 63029a4 into opendilab:main Jun 27, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants