I would like to ask about issues related to observation and actions during the training process.

[tobottyx]

"In the above image, there is an agent_pos in the observation, which has the same dimension as in the action. What is the difference between the two, and what are they used for, respectively?"
I sincerely hope to receive your response

[YanjieZe]

Agent pos is the status of the robot. The action is to control the robot to the target status