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.

Sign up for GitHub

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

Jump to bottom

[RLlib] Cleanup examples folder #10: Add custom_rl_module.py example script and matching RLModule example class (tiny CNN).. #45774

Merged
merged 14 commits into from
Jun 7, 2024
Merged

[RLlib] Cleanup examples folder #10: Add custom_rl_module.py example script and matching RLModule example class (tiny CNN).. #45774

merged 14 commits into from
Jun 7, 2024
+362 −108

Conversation

sven1977
Copy link
Contributor

@sven1977 sven1977 commented Jun 6, 2024 •
edited
Loading

Cleanup examples folder #10: Add custom_rl_module.py example script and matching RLModule example class (tiny CNN)..

Why are these changes needed?

Related issue number

Checks

  • I've signed off every commit(by using the -s flag, i.e., git commit -s) in this PR.
  • I've run scripts/format.sh to lint the changes in this PR.
  • I've included any doc changes needed for https://docs.ray.io/en/master/.
    • I've added any new APIs to the API Reference. For example, if I added a
      method in Tune, I've added it in doc/source/tune/api/ under the
      corresponding .rst file.
  • I've made sure the tests are passing. Note that there might be a few flaky tests, see the recent failures at https://flakey-tests.ray.io/
  • Testing Strategy
    • Unit tests
    • Release tests
    • This PR is not tested :(

@sven1977
wip
16ec8ad 
Signed-off-by: sven1977 <[email protected]>
@sven1977
wip
0af3228 
Signed-off-by: sven1977 <[email protected]>
@sven1977
Merge branch 'master' of https://github.com/ray-project/ray into clea…
bbd5ec2 
…nup_examples_folder_10_custom_rl_module.py
@sven1977
Merge branch 'master' of https://github.com/ray-project/ray into clea…
375c7ba 
…nup_examples_folder_10_custom_rl_module.py

Signed-off-by: sven1977 <[email protected]>
@sven1977
wip
df4192b 
Signed-off-by: sven1977 <[email protected]>
@sven1977
Merge branch 'master' of https://github.com/ray-project/ray into clea…
65f32d2 
…nup_examples_folder_10_custom_rl_module.py
@sven1977
LINT and test case and docstring
b8b459f 
Signed-off-by: sven1977 <[email protected]>
simonsays1980
simonsays1980 approved these changes Jun 6, 2024
View reviewed changes
Copy link
Collaborator

@simonsays1980 simonsays1980 left a comment

Choose a reason for hiding this comment

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

LGTM.

rllib/core/rl_module/torch/torch_rl_module.py Outdated
# The default implementation is to return TorchCategorical for Discrete action
# spaces and TorchDiagGaussian for Box action spaces. For all other spaces,
# raise a NotImplementedError
if isinstance(self.config.action_space, gym.spaces.Discrete):
Copy link
Collaborator

Choose a reason for hiding this comment

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

Why not using TorchMultiCategorical and TorchMultiDistribution - things that get assembled inside of the Catalog?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Not sure either, tbh. I just wanted to get the most simple setup automated. I feel like users that just want to "hack together an RLModule" should not be concerned about picking the categorical distr for their CartPole action space :)

Yes, we should extend this method to even more decent defaults, I think.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Let's continue brainstorming how to simplify the general RLModule experience for the user ...

rllib/env/single_agent_env_runner.py
@@ -91,12 +91,9 @@ def __init__(self, config: AlgorithmConfig, **kwargs):
try:
module_spec: SingleAgentRLModuleSpec = self.config.rl_module_spec
module_spec.observation_space = self._env_to_module.observation_space
# TODO (simon): The `gym.Wrapper` for `gym.vector.VectorEnv` should
Copy link
Collaborator

Choose a reason for hiding this comment

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

Great that this is gone now.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Yeah, it didn't seem to be a problem anymore (e.g. for PPO Pendulum, everything looks completely fine w/o any weird space errors on the Box actions). So I removed this comment.

@sven1977 sven1977 enabled auto-merge (squash) June 6, 2024 15:55
@github-actions github-actions bot added the go add ONLY when ready to merge, run all tests label Jun 6, 2024
@sven1977
Merge branch 'master' of https://github.com/ray-project/ray into clea…
4f0f949 
…nup_examples_folder_10_custom_rl_module.py
@sven1977
Merge branch 'master' of https://github.com/ray-project/ray into clea…
ee86f90 
…nup_examples_folder_10_custom_rl_module.py
@sven1977
wip
6f4672a 
Signed-off-by: sven1977 <[email protected]>
@sven1977
wip
a30f9b6 
Signed-off-by: sven1977 <[email protected]>
@github-actions github-actions bot disabled auto-merge June 7, 2024 07:00
@sven1977
fixes
587b5f0 
Signed-off-by: sven1977 <[email protected]>
@sven1977
Merge branch 'master' of https://github.com/ray-project/ray into clea…
5994553 
…nup_examples_folder_10_custom_rl_module.py
@sven1977 sven1977 merged commit ef54ee5 into ray-project:master Jun 7, 2024
6 checks passed
@sven1977 sven1977 deleted the cleanup_examples_folder_10_custom_rl_module.py branch June 7, 2024 12:30
richardsliu pushed a commit to richardsliu/ray that referenced this pull request Jun 12, 2024
@sven1977 @richardsliu
[RLlib] Cleanup examples folder ray-project#10: Add `custom_rl_module…
5a409a3 
….py` example script and matching RLModule example class (tiny CNN).. (ray-project#45774)

Signed-off-by: Richard Liu <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@simonsays1980 simonsays1980 simonsays1980 approved these changes

@ArturNiederfahrenhorst ArturNiederfahrenhorst Awaiting requested review from ArturNiederfahrenhorst

Assignees

@simonsays1980 simonsays1980

Labels
go add ONLY when ready to merge, run all tests
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@sven1977 @simonsays1980