feat(off-policy): fix final_obsevation setting and support evaluation times configuation

[Gaiejj]

Description

• feat: support evaluation episodes configuration
• fix: fix final observation setting in off-policy algorithms

Motivation and Context

• Previously the off-policy algorithms must evaluate once per episode, This pull request would set the times of evaluation as a configuration. If you do not want to evaluate during training process, please set it to 0.

• We process the final_observation to address the issue of the end of trajectory. However, not all environments have the key final_observation in the info of step function. So we fix it by a simple if-else judgement.

• 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? Put an x in all the boxes that 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)

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.
• I have reformatted the code using make format. (required)
• I have checked the code using make lint. (required)
• I have ensured make test pass. (required)

[muchvo]

LGTM.