[Algorithm] Td3

[BY571]

Description

Adding Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm.
Creating:

• Example script
• Adding TD3Loss objective class
• Adding make_td3_loss helper function
• Adding make_td3_actor helper function
• Creating TD3Model data class
• Adapting the AdditiveGaussianWrapper to accept mean and std for the normal distribution
• Adding TD3MlpQNet Model
• Tested algorithm for convergence

Performance looks good at the beginning of the training but becomes very unstable at the end. Did try some other parameter settings but could not resolve the instabilities until now.

Motivation and Context

This PR closes an open issue: close #18.

• I have raised an issue to propose this change (required for new features and bug fixes)

Types of changes

What types of changes does your code introduce? Remove all that do not apply:

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds core functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation (update in the documentation)
• Example (update in the folder of examples)

Checklist

Go over all the following points, and put an x in all the boxes that apply.
If you are unsure about any of these, don't hesitate to ask. We are here to help!

• I have read the CONTRIBUTION guide (required)
• My change requires a change to the documentation.
• I have updated the tests accordingly (required for a bug fix or a new feature).
• I have updated the documentation accordingly.

[facebook-github-bot]

Hi @BY571!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at [email protected]. Thanks!

[facebook-github-bot]

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!

[vmoens]

For the formatting, refer to instructions :)

[vmoens]

I think you have committed a log file :)
Let me know if there's anything i can do to help -- I can do a review even if the code is still a draft if you'd like

[BY571]

I think you have committed a log file :) Let me know if there's anything i can do to help -- I can do a review even if the code is still a draft if you'd like

Sure, you can review it already! Just trying to fix the last formatting issue.

[codecov]

Codecov Report

Merging #684 (5d1b995) into main (37da520) will increase coverage by 3.68%.
The diff coverage is 96.51%.

@@            Coverage Diff             @@
##             main     #684      +/-   ##
==========================================
+ Coverage   85.15%   88.83%   +3.68%     
==========================================
  Files         123      124       +1     
  Lines       21167    21364     +197     
==========================================
+ Hits        18024    18978     +954     
+ Misses       3143     2386     -757     

Flag	Coverage Δ
habitat-gpu	24.74% <20.83%> (-0.02%)	⬇️
linux-brax	29.31% <20.83%> (-0.05%)	⬇️
linux-cpu	85.32% <95.02%> (?)
linux-gpu	86.30% <96.51%> (+61.43%)	⬆️
linux-jumanji	30.08% <20.83%> (-0.06%)	⬇️
linux-outdeps-gpu	72.47% <95.02%> (+0.21%)	⬆️
linux-stable-cpu	85.18% <95.02%> (?)
linux-stable-gpu	85.95% <95.02%> (?)
linux_examples-gpu	42.59% <25.00%> (-0.11%)	⬇️
macos-cpu	85.08% <95.02%> (?)
olddeps-gpu	75.49% <20.39%> (-0.54%)	⬇️

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

Impacted Files	Coverage Δ
torchrl/objectives/utils.py	83.44% <ø> (ø)
torchrl/modules/tensordict_module/exploration.py	77.77% <83.33%> (+0.31%)	⬆️
test/test_cost.py	96.32% <96.89%> (+0.11%)	⬆️
torchrl/objectives/td3.py	96.92% <96.92%> (ø)
torchrl/objectives/__init__.py	100.00% <100.00%> (ø)
torchrl/envs/common.py	83.12% <0.00%> (+0.25%)	⬆️
torchrl/modules/distributions/continuous.py	85.65% <0.00%> (+0.39%)	⬆️
torchrl/data/tensor_specs.py	84.25% <0.00%> (+1.10%)	⬆️
examples/dreamer/dreamer_utils.py	78.53% <0.00%> (+1.69%)	⬆️
... and 17 more

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

[vmoens]

LGTM thanks for this!