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

[RLlib] Move DQN into the TargetNetworkAPI (and deprecate RLModuleWithTargetNetworksInterface). #46752

Merged
merged 2 commits into from
Jul 23, 2024

Conversation

sven1977
Copy link
Contributor

Move DQN into the TargetNetworkAPI (and deprecate RLModuleWithTargetNetworksInterface).

  • Also deprecate TorchDDPRLModuleWithTargetNetworksInterface.

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 :(

Signed-off-by: sven1977 <[email protected]>
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. Can we test, if this still works out with multi-learner setups?

@@ -105,7 +106,7 @@ def __init__(self, algo_class=None):
self.num_multi_gpu_tower_stacks = 1
self.minibatch_buffer_size = 1
self.num_sgd_iter = 1
self.target_update_frequency = 1
self.target_network_update_freq = 1
Copy link
Collaborator

Choose a reason for hiding this comment

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

Way better!

lambda mid, module: (
module.sync_target_networks(tau=1.0)
if hasattr(module, "sync_target_networks")
lambda mid, mod: (
Copy link
Collaborator

Choose a reason for hiding this comment

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

Nice!

Copy link
Collaborator

Choose a reason for hiding this comment

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

And .... gone :)

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, this was such a hack.

@sven1977
Copy link
Contributor Author

Good point! WE haven't re-merged the +GPU +multi-GPU +multi-agent tests for DQN + SAC yet, correct?

Signed-off-by: sven1977 <[email protected]>
@sven1977 sven1977 enabled auto-merge (squash) July 23, 2024 12:03
@github-actions github-actions bot added the go add ONLY when ready to merge, run all tests label Jul 23, 2024
@simonsays1980
Copy link
Collaborator

Good point! WE haven't re-merged the +GPU +multi-GPU +multi-agent tests for DQN + SAC yet, correct?

No, we haven't because they are flaky on the CI machines.

@sven1977 sven1977 merged commit 54e314f into ray-project:master Jul 23, 2024
7 checks passed
@sven1977 sven1977 deleted the finish_target_net_api_for_dqn branch July 23, 2024 18:56
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
go add ONLY when ready to merge, run all tests
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants