Description

Implements a transform that adds a user-defined target return to the tensordict.

Motivation and Context

For goal-conditioned RL you may want to specify a target return that the agent should achieve in one episode. This transform adds such a target return to the tensordict which can be then used as an additional input for the agent.
With the mode input, it offers the option to keep the target return constant during the whole episode or reduce reduce the target return at each step by the reward obtained.
This transform is useful for mentioned goal-conditioned RL but also Upside-Down RL or the Decision Transformer.

• 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? Remove all that do not 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)
• Example (update in the folder of examples)

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.