In their work Continuous Deep Q-Learning with Model-based Acceleration, the author demonstrate great results of applying Imagination Rollouts for model-based acceleration of learning. They test their algorithm on manipulation tasks in a Mujoco simulation. I wonder whether similar accelaration would be possible in classic environments like Pendulum-v0.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.