feat(reinforcement learning): ability to train and use an agent trained by RL

[yakir4123]

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[xsa-dev]

Successfully assembled, but had to change some versions and comment out some tests: https://github.com/xsa-dev/jesse/pull/40/commits/5ee147ada3040bba1b0f2abfec2d265044384717

[xsa-dev]

@yakir4123 @saleh-mir could you create a separate branch for the reinforce algorithm?

[yakir4123]

You mean update it to the last version?

[xsa-dev]

You mean update it to the last version?

Yes, exactly