I've been trying to learn the control policy for custom datasets. And I can get quaternion values right in the file params.xml. I either get the wrong translation or even though visually the translations are more or less similar to the translations with the vista dataset. Nonetheless, the total reward eventually stuck around five and never recover afterward.
I've been trying to learn the control policy for custom datasets. And I can get quaternion values right in the file params.xml. I either get the wrong translation or even though visually the translations are more or less similar to the translations with the vista dataset. Nonetheless, the total reward eventually stuck around five and never recover afterward.