[Feature] Jumanji envs #674

yingchenlin · 2022-11-14T13:45:12Z

Description

Built spec for Jumanji state.
Convert data between Torch RL TensorDict and Jumaji state.
Add support for seeding.
Allow multi-dimensional batch_size.

* transform step function * amend * amend * amend * amend * amend

…ctor_next_bis'

# Conflicts: # torchrl/data/tensor_specs.py

# Conflicts: # test/_utils_internal.py # torchrl/data/tensor_specs.py # torchrl/envs/gym_like.py # torchrl/envs/transforms/transforms.py

# Conflicts: # .circleci/config.yml # docs/source/reference/envs.rst

codecov · 2022-11-18T14:24:47Z

Codecov Report

Merging #674 (4a56a86) into main (26881b3) will increase coverage by 0.11%.
The diff coverage is 90.85%.

@@            Coverage Diff             @@
##             main     #674      +/-   ##
==========================================
+ Coverage   87.78%   87.90%   +0.11%     
==========================================
  Files         119      120       +1     
  Lines       20201    20491     +290     
==========================================
+ Hits        17733    18012     +279     
- Misses       2468     2479      +11

Flag	Coverage Δ
habitat-gpu	`24.08% <18.47%> (-0.14%)`	⬇️
linux-cpu	`84.71% <27.76%> (-0.83%)`	⬇️
linux-gpu	`85.60% <27.76%> (-0.85%)`	⬇️
linux-jumanji	`29.07% <89.80%> (?)`
linux-outdeps-gpu	`72.05% <20.50%> (-0.76%)`	⬇️
linux-stable-cpu	`84.56% <27.76%> (-0.83%)`	⬇️
linux-stable-gpu	`85.27% <27.76%> (-0.84%)`	⬇️
macos-cpu	`84.38% <26.49%> (-0.88%)`	⬇️
olddeps-gpu	`74.34% <26.49%> (-0.74%)`	⬇️

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

Impacted Files	Coverage Δ
torchrl/envs/libs/gym.py	`80.71% <ø> (ø)`
torchrl/data/tensor_specs.py	`84.72% <69.23%> (+1.74%)`	⬆️
torchrl/envs/libs/jumanji.py	`90.43% <90.43%> (ø)`
test/_utils_internal.py	`89.74% <93.75%> (+3.49%)`	⬆️
test/test_libs.py	`96.30% <94.52%> (-0.68%)`	⬇️
test/test_collector.py	`98.63% <100.00%> (+<0.01%)`	⬆️
torchrl/envs/common.py	`83.64% <100.00%> (ø)`

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

vmoens

Just a couple of comments

torchrl/envs/libs/jumanji.py

.circleci/config.yml

vmoens

Great stuff! A huge plus for the library!

* 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>

* 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>

vmoens and others added 26 commits November 2, 2022 17:17

init

2f1fac8

[jumanji] add support for seeding and batch_size

df4760d

init

e6f4b96

[Feature] Nested composite spec (pytorch#654)

294dbf0

data conversion between Jumanji and TorchRL

d8bdb05

Merge branch 'main' into refactor_next_bis

080fb47

[Feature] Move transform.forward to transform.step (pytorch#660)

fce326b

* transform step function * amend * amend * amend * amend * amend

feedback from vmoens

d569512

linter fix

428c1d3

amend

b3b36cd

amend

16ef495

fix dtype

47da10f

amend

4617bb6

Merge branch 'jumanji' of github.com:yingchenlin/rl into jumanji

a466faf

fixing key names

ed9ccbc

fixing key names

b6902ae

fix tensor shape

aa02748

Merge branch 'keyname_fix' into jumanji

9765655

tests workflow

8396a32

Merge branch 'keyname_fix' into refactor_next_bis

a9d3b2f

Merge branch 'refactor_next_bis', remote-tracking branch 'origin/refa…

8431af2

…ctor_next_bis'

t checkout Merge branch 'main' of github.com:pytorch/rl

710cfc1

Merge remote-tracking branch 'yingchenlin/jumanji' into jumanji

3d75f9d

Merge branch 'main' into jumanji

3837d3c

Merge remote-tracking branch 'origin/main' into jumanji

f905f27

# Conflicts: # torchrl/data/tensor_specs.py

bug fix

b31f588

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 14, 2022

vmoens added 3 commits November 15, 2022 14:04

Merge branch 'main' into jumanji

9afb313

Merge branch 'main' into jumanji

485fc97

amend

3220b0e

This was referenced Nov 15, 2022

[Feature] Jumanji envs #638

Closed

[Feature] Jumanji: add support for seeding and batch_size #648

Closed

vmoens added 10 commits November 16, 2022 12:14

Merge branch 'main' into jumanji

01683c9

# Conflicts: # test/_utils_internal.py # torchrl/data/tensor_specs.py # torchrl/envs/gym_like.py # torchrl/envs/transforms/transforms.py

amend

73bb98b

amend

3513800

cleanup

00d85e5

cleanup

0c9cd8a

bf

6dc0a94

bf

6249102

bf

e242a1f

bf

704fd80

lint

b887286

vmoens added the enhancement New feature or request label Nov 18, 2022

vmoens added 2 commits November 18, 2022 11:50

Merge branch 'main' into jumanji

037c4f4

# Conflicts: # .circleci/config.yml # docs/source/reference/envs.rst

amend

020404e

vmoens reviewed Nov 18, 2022

View reviewed changes

torchrl/envs/libs/jumanji.py Outdated Show resolved Hide resolved

torchrl/envs/libs/jumanji.py Outdated Show resolved Hide resolved

torchrl/envs/libs/jumanji.py Outdated Show resolved Hide resolved

.circleci/config.yml Outdated Show resolved Hide resolved

Ying-Chen Lin and others added 5 commits November 18, 2022 23:06

refactor

51757ba

Merge branch 'jumanji' of github.com:yingchenlin/rl into jumanji

b14a029

refactor

a6bd1f5

refactor

b58ee1b

amend

60f0bec

vmoens approved these changes Nov 19, 2022

View reviewed changes

vmoens added 3 commits November 19, 2022 06:53

amend

d845598

amend

24c293f

amend

4a56a86

vmoens merged commit f5d98af into pytorch:main Nov 19, 2022

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Feature] Jumanji envs #674

[Feature] Jumanji envs #674

yingchenlin commented Nov 14, 2022

codecov bot commented Nov 18, 2022 •

edited

Loading

vmoens left a comment

vmoens left a comment

[Feature] Jumanji envs #674

[Feature] Jumanji envs #674

Conversation

yingchenlin commented Nov 14, 2022

Description

codecov bot commented Nov 18, 2022 • edited Loading

Codecov Report

vmoens left a comment

Choose a reason for hiding this comment

vmoens left a comment

Choose a reason for hiding this comment

codecov bot commented Nov 18, 2022 •

edited

Loading