Remove MuJoCo dependency from SQIL notebook

[AdamGleave]

Description

Fixes #798.

WIP: @ernestum can you make a HuggingFace dataset ppo-Pendulum-v1 out of the same-name model? I think that will be enough to make this notebook work. I'm not sure how you generated datasets so deferring to you on this.

[ernestum]

Pushed it here. Let's see what it does ...

[ernestum]

Seems like the SQIL notebook tests pass (even though other tests still fail due to issues addressed in other PRs.

[Rocamonde]

this looks fine to me, even though I'm missing context so I cannot speak for the high-level intent of whether replacing it with the Pendulum is the right choice. Only thing seems to be that you're no longer using seals? Is this intentional?

[ernestum]

The context is in the linked issue #798. Basically we just wanted to get rid of the MuJoCo dependency in the test pipeline. So we just replaced the environment with anything basic that is not MuJoCO.

[codecov]

Codecov Report

Merging #800 (e14c27a) into master (5b0b531) will decrease coverage by 0.05%.
Report is 11 commits behind head on master.
The diff coverage is 96.69%.

@@            Coverage Diff             @@
##           master     #800      +/-   ##
==========================================
- Coverage   96.38%   96.33%   -0.05%     
==========================================
  Files          95       98       +3     
  Lines        8901     9177     +276     
==========================================
+ Hits         8579     8841     +262     
- Misses        322      336      +14     

Files	Coverage Δ
src/imitation/algorithms/adversarial/common.py	96.84% <100.00%> (+0.01%)	⬆️
src/imitation/algorithms/bc.py	98.31% <100.00%> (-0.02%)	⬇️
src/imitation/algorithms/dagger.py	100.00% <100.00%> (ø)
src/imitation/algorithms/mce_irl.py	96.17% <100.00%> (ø)
src/imitation/algorithms/sqil.py	100.00% <100.00%> (ø)
src/imitation/data/huggingface_utils.py	100.00% <ø> (ø)
src/imitation/data/wrappers.py	100.00% <100.00%> (ø)
src/imitation/policies/interactive.py	100.00% <100.00%> (ø)
src/imitation/policies/replay_buffer_wrapper.py	100.00% <100.00%> (ø)
src/imitation/rewards/reward_nets.py	100.00% <100.00%> (ø)
... and 33 more

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