Added PPO+LSTM, plus training example

[roger-creus]

Description

I have added a new agent -- PPO + LSTM, together with the new EpisodicRolloutBuffer, which is similar to VanillaRolloutBuffer but samples entire trajectories instead of random transitions in order to train the LSTM appropriately.

I have also added an example notebook to train it on Atari - Space Invaders, which achieves the following results:

In this case, it performs very similarly to vanilla PPO:

Motivation and Context

PPO LSTM can achieve better performance than PPO in partially observed environments.

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

Types of changes

• [ ] Bug fix (non-breaking change which fixes an issue)
• [x] New feature (non-breaking change which adds functionality)
• [ ] Breaking change (fix or feature that would cause existing functionality to change)
• [ ] Documentation (update in the documentation)

Checklist

• [x] I've read the CONTRIBUTION guide (required)
• [ ] I have updated the changelog accordingly (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.
• [ ] I have opened an associated PR on the rllte-hub repository (if necessary)
• [x] I have reformatted the code using make format (required)
• [x] I have checked the codestyle using make check-codestyle and make lint (required)
• [] I have ensured make pytest and make type both pass. (required)
• [ ] I have checked that the documentation builds using make doc (required)

Note: You can run most of the checks using make commit-checks.

Note: we are using a maximum length of 127 characters per line