[FEATURE] Investigate Using TrajectoryDataset for Recurrent Systems

Feature

Investigating using reverb.TrajectoryDataset for all recurrent systems.

Proposal

Change make_dataset_iterator to use reverb.TrajectoryDataset since it appears that TrajectoryDataset works better (faster trainer speed) when using the SequenceAdder.

Definition of done

All recurrent systems use reverb.TrajectoryDataset , with a full benchmark of performance results.

Mandatory checklist before making a PR

• [ ] The success criteria laid down in “Definition of done” are met.
• [ ] Code is documented - docstrings for methods and classes, static types for arguments.
• [ ] Code is tested - unit, integration and/or functional tests are added.
• [ ] Documentation is updated - README, CONTRIBUTING, or other documentation.
• [ ] All functional tests are green.
• [ ] Link experiment/benchmarking after implementation (optional).

Links / references / screenshots