Update TD3/DDPG/DQN defaults for consistency

[araffin]

Description

closes #1769
closes #1562

EDIT: WIP report is here: https://wandb.ai/openrlbenchmark/sbx/reports/SBX-TD3-RL-Zoo-v2-3-0a0-vs-SB3-TD3-RL-Zoo-2-2-1---Vmlldzo2MjUyNTQx

Note: I didn't change the default network architecture because it would break all pre-trained models where net_arch was not specified properly.

TODO:

• A benchmark still need to be done for TD3/DDPG to check the impact of the change, but I've got initial results with SBX where no big change is expected
• Update the RL Zoo default hyperparams (independent of this PR)

Motivation and Context

• 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)
• 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

• 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 SB3-Contrib repository (if necessary)
• I have opened an associated PR on the RL-Zoo3 repository (if necessary)
• I have reformatted the code using make format (required)
• 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

[araffin]

Small update, it seems that we should keep lr=1e-3, will continue more quantitative experiments in Jan (also comparing with different network sizes), have nice holidays =)

See report https://wandb.ai/openrlbenchmark/sbx/reports/SBX-TD3-RL-Zoo-v2-3-0a0-vs-SB3-TD3-RL-Zoo-2-2-1---Vmlldzo2MjUyNTQx

cc @Kallinteris-Andreas

[Kallinteris-Andreas]

I would like to also see SAC tested with lr=1e-3

[araffin]

I would like to also see SAC tested with lr=1e-3

Here you go (3 seeds only for now), there seems to be a small improvement for HC and Ant but need more seeds for confirmation.
https://wandb.ai/openrlbenchmark/sbx/reports/SBX-SAC-influence-of-learning-rate--Vmlldzo2NDg1MjUz

Influence of the neural network size for TD3:
https://wandb.ai/openrlbenchmark/sbx/reports/SBX-TD3-Influence-of-policy-net--Vmlldzo2NDg1Mzk3

Not much to say, small impact only.