Skip to content

Conversation

@vmoens
Copy link
Collaborator

@vmoens vmoens commented Nov 21, 2022

Description

Implements the MPPI planner

@nicklashansen

vmoens and others added 9 commits November 18, 2022 13:59
#686)

* cnn forward fix

* more general code

* cnn testing

* precommit run check

* convnet tests
* Add standard_normal

* give attribute access

* Update standard_normal

* Update tests

* Fix tests

* Address in-place scaling of reward

* Improvise tests
@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Nov 21, 2022
ordinskiy and others added 9 commits November 21, 2022 21:09
…ons (#691)

* [Refactoring] Replace gym version checking with decorated functions (#)

Initial commit. Only tests.

* Refactoring in gym.py

* More refactoring in gym.py

* Completed refactoring

* amend

* amend
* Pull tensordict docs into TorchRL docs

* Add banner for tensordict docs
# Conflicts:
#	.circleci/unittest/linux_examples/scripts/run_test.sh
#	torchrl/envs/transforms/transforms.py
@codecov
Copy link

codecov bot commented Nov 23, 2022

Codecov Report

Merging #694 (a759123) into tdmpc (f3f174a) will increase coverage by 64.51%.
The diff coverage is 92.29%.

@@             Coverage Diff             @@
##            tdmpc     #694       +/-   ##
===========================================
+ Coverage   24.22%   88.73%   +64.51%     
===========================================
  Files          80      122       +42     
  Lines       10094    20839    +10745     
===========================================
+ Hits         2445    18491    +16046     
+ Misses       7649     2348     -5301     
Flag Coverage Δ
habitat-gpu 24.42% <23.36%> (+0.20%) ⬆️
linux-cpu 84.87% <61.71%> (?)
linux-gpu 85.75% <61.86%> (?)
linux-jumanji 29.36% <67.72%> (?)
linux-outdeps-gpu 72.51% <53.57%> (?)
linux-stable-cpu 84.73% <61.71%> (?)
linux-stable-gpu 85.43% <61.86%> (?)
linux_examples-gpu 43.12% <47.51%> (?)
macos-cpu 84.54% <60.40%> (?)
olddeps-gpu 74.60% <59.85%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
torchrl/trainers/helpers/replay_buffer.py 94.44% <ø> (ø)
torchrl/trainers/helpers/envs.py 74.87% <60.00%> (ø)
torchrl/data/tensor_specs.py 84.72% <69.23%> (+54.50%) ⬆️
torchrl/envs/libs/gym.py 82.02% <79.24%> (+56.13%) ⬆️
torchrl/envs/transforms/transforms.py 87.12% <83.33%> (+60.85%) ⬆️
torchrl/envs/libs/jumanji.py 90.43% <90.43%> (ø)
torchrl/data/replay_buffers/storages.py 83.84% <90.47%> (+60.01%) ⬆️
test/test_libs.py 96.24% <95.40%> (+66.59%) ⬆️
torchrl/modules/planners/cem.py 97.95% <96.29%> (+74.14%) ⬆️
test/_utils_internal.py 91.75% <97.22%> (+63.00%) ⬆️
... and 114 more

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more

@vmoens vmoens changed the title [WIP] MPPI Planner [Feature] MPPI Planner Nov 23, 2022
@vmoens vmoens added enhancement New feature or request new algo New algorithm request or PR labels Nov 23, 2022
@vmoens vmoens merged commit c60ace5 into tdmpc Nov 23, 2022
@vmoens vmoens deleted the planner branch November 24, 2022 08:44
vmoens added a commit that referenced this pull request Jan 5, 2023
* init

* tests1

* run examples in tests

* [Feature] MPPI Planner (#694)

* amend

* [BugFix] ConvNet forward method with tensors of more than 4 dimensions (#686)

* cnn forward fix

* more general code

* cnn testing

* precommit run check

* convnet tests

* [Feature] add `standard_normal` for RewardScaling (#682)

* Add standard_normal

* give attribute access

* Update standard_normal

* Update tests

* Fix tests

* Address in-place scaling of reward

* Improvise tests

* [Feature] Jumanji envs (#674)

* amend

* [Feature] Default collate_fn (#688)

* init

* amend

* amend

* [BugFix] Fix Examples (#687)

* amend

* [Refactoring] Replace direct gym version checks with decorated functions (#691)

* [Refactoring] Replace gym version checking with decorated functions (#)

Initial commit. Only tests.

* Refactoring in gym.py

* More refactoring in gym.py

* Completed refactoring

* amend

* amend

* Version 0.0.3 (#696)

* [Docs] Host TensorDict docs inside TorchRL docs (#693)

* Pull tensordict docs into TorchRL docs

* Add banner for tensordict docs

* [BugFix] Fix docs build (#698)

* [BugFix] Proper error messages for orphan transform creation (#697)

* amend

* [Feature] Append, init and insert transforms in ReplayBuffer (#695)

* lint

Co-authored-by: albertbou92 <albertbou92@users.noreply.github.com>
Co-authored-by: Aditya Gandhamal <61016383+adityagandhamal@users.noreply.github.com>
Co-authored-by: yingchenlin <yc.jon.lin@gmail.com>
Co-authored-by: Sergey Ordinskiy <113687736+ordinskiy@users.noreply.github.com>
Co-authored-by: Tom Begley <tomcbegley@gmail.com>
Co-authored-by: Alan Schelten <alan@schelten.net>

* lint

Co-authored-by: albertbou92 <albertbou92@users.noreply.github.com>
Co-authored-by: Aditya Gandhamal <61016383+adityagandhamal@users.noreply.github.com>
Co-authored-by: yingchenlin <yc.jon.lin@gmail.com>
Co-authored-by: Sergey Ordinskiy <113687736+ordinskiy@users.noreply.github.com>
Co-authored-by: Tom Begley <tomcbegley@gmail.com>
Co-authored-by: Alan Schelten <alan@schelten.net>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. enhancement New feature or request new algo New algorithm request or PR

Projects

None yet

Development

Successfully merging this pull request may close these issues.

9 participants