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] Add DTTorchPolicy #27889

Merged
merged 26 commits into from
Aug 17, 2022
Merged

[RLlib] Add DTTorchPolicy #27889

merged 26 commits into from
Aug 17, 2022

Conversation

charlesjsun
Copy link
Contributor

Why are these changes needed?

Add DTTorchPolicy for DT.

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 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 :(

@charlesjsun
Added segmentation buffer
d6d446c 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
added stuff
bddf887 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
torch model
ba9d46f 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
address PR reviews
3e4cda6 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
add attention output and causal test
358ef40 
Signed-off-by: Charles Sun <[email protected]>
kouroshHakha
kouroshHakha reviewed Aug 16, 2022
View reviewed changes
Copy link
Contributor

@kouroshHakha kouroshHakha left a comment

Choose a reason for hiding this comment

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

Thanks for the good documentation which made it easy to follow along. Please address the remaining comments.

rllib/algorithms/dt/dt_torch_policy.py Outdated Show resolved Hide resolved
rllib/algorithms/dt/dt_torch_policy.py Show resolved Hide resolved
rllib/algorithms/dt/dt_torch_policy.py Outdated Show resolved Hide resolved
rllib/algorithms/dt/tests/test_dt_policy.py Outdated Show resolved Hide resolved
rllib/algorithms/dt/tests/test_dt_policy.py Outdated Show resolved Hide resolved
@charlesjsun
fix test imports
99a89c3 
Signed-off-by: Charles Sun <[email protected]>
kouroshHakha
kouroshHakha approved these changes Aug 16, 2022
View reviewed changes
Copy link
Contributor

@kouroshHakha kouroshHakha left a comment

Choose a reason for hiding this comment

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

@charlesjsun Great work in addressing everything man! @richardliaw Can we get this in the merge queue once all the tests pass again?

@charlesjsun
fix merge conflict
7cdf71f 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
tmp
7d33c13
@charlesjsun
Add tests
5eada7c 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
revert mingpt
09d8088 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
fix typo and add initial rtg method
1301201 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
dict update
75fb7b5 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
changed postprocess_trajectory to process dones
cc78527 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
lint
e535dd6 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
minor test cleanup
0b23dba 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
loss function simplification
731cb41 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
fix imports in test
6242bfc 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
updated compute_actions_from_input_dict
7cf3f69 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
added test and coef
41d9f92 
Signed-off-by: Charles Sun <[email protected]>
@charlesjsun
fix merge conflict
96193b9 
Signed-off-by: Charles Sun <[email protected]>
@richardliaw richardliaw merged commit 9330d8f into ray-project:master Aug 17, 2022
Stefan-1313 pushed a commit to Stefan-1313/ray_mod that referenced this pull request Aug 18, 2022
@charlesjsun
[RLlib] Add DTTorchPolicy (ray-project#27889)
68a849a 
Signed-off-by: Stefan van der Kleij <[email protected]>
Signed-off-by: Stefan van der Kleij <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@kouroshHakha kouroshHakha kouroshHakha approved these changes

@sven1977 sven1977 Awaiting requested review from sven1977 sven1977 is a code owner

@gjoliver gjoliver Awaiting requested review from gjoliver

@avnishn avnishn Awaiting requested review from avnishn

@ArturNiederfahrenhorst ArturNiederfahrenhorst Awaiting requested review from ArturNiederfahrenhorst

@smorad smorad Awaiting requested review from smorad

@maxpumperla maxpumperla Awaiting requested review from maxpumperla

@krfricke krfricke Awaiting requested review from krfricke

Assignees

@sven1977 sven1977

@kouroshHakha kouroshHakha

@avnishn avnishn

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@charlesjsun @kouroshHakha @richardliaw @sven1977 @avnishn