[RLlib] Add simple curriculum learning API and example script. #15740
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…iculum_learning_api
…iculum_learning_api
…iculum_learning_api
sven1977
added
the
tests-ok
richardliaw
reviewed
May 14, 2021
rllib/agents/trainer_template.py
Outdated
|
|
||
| # Check `env_task_fn` for possible update of the env's task. | ||
| if self.config["env_task_fn"] is not None: | ||
| assert callable(self.config["env_task_fn"]) |
There was a problem hiding this comment.
assertions in code can be a bit unwieldy, especially when the users see it.
I would consider writing a special check function that also prints a user friendly message.
richardliaw
reviewed
May 14, 2021
Comment on lines
32
to
34
| parser.add_argument("--stop-iters", type=int, default=50) | ||
| parser.add_argument("--stop-timesteps", type=int, default=200000) | ||
| parser.add_argument("--stop-reward", type=float, default=10000.0) |
There was a problem hiding this comment.
Done. I'll do this for all the other example scripts in a separate PR.
richardliaw
reviewed
May 14, 2021
|
|
||
| if args.as_test: | ||
| check_learning_achieved(results, args.stop_reward) | ||
| ray.shutdown() |
There was a problem hiding this comment.
you don't need this right?
- in local case, ray will shutdown when process exits
- in remote case, ray will disconnect when process exits
There was a problem hiding this comment.
I remember a time when not calling shutdown at the end of tests would lead to re-init errors when we run these tests in e.g. the CI.
richardliaw
approved these changes
May 14, 2021
…iculum_learning_api
…iculum_learning_api
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds:
that determines, whether the env should be set to a new task.
Why are these changes needed?
Related issue number
Checks
scripts/format.shto lint the changes in this PR.