Does anybody have an example for the input format for the following scenario:

• Tensorflow-Ray RL model deployed
• Custom RL environment
• The state of the environment is a Python Dictionary
• An example input:

input = {
"inputs": {
"observations": {"one": [[1.0, 1.0]], "two": [[1.0,1.0,1.0]]},
"prev_action": [0, 0],
"is_training": False,
"prev_reward": -1,
"seq_lens": -1,
"timestep": 1,
}
}

However I receive the error: "An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from primary with message "{ "error": "instances is a plain list, but expecting list of objects as multiple input tensors required as per tensorinfo_map"}"".

Apparently, there is no example for such as case in the repository.

Thanks in advance.