Learning optimal policies with a trained model

Linear/Dynamic/Stochastic programming (all examples of model-driven - which don’t use a simulation but instead a pre-existing model)

References and further reading

Deisenroth, Marc Peter, Dieter Fox, and Carl Edward Rasmussen. 2015. “Gaussian Processes for Data-Efficient Learning in Robotics and Control.” IEEE Transactions on Pattern Analysis and Machine Intelligence 37 (2): 408–23. https://doi.org/10.1109/TPAMI.2013.218.

Ha, David, and Jürgen Schmidhuber. 2018. World Models. arXiv preprint. https://arxiv.org/abs/1803.10122.

Levine, Sergey, Aviral Kumar, George Tucker, and Justin Fu. 2020. Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems. arXiv preprint. https://arxiv.org/abs/2005.01643.

Sutton, Richard S., and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. 2nd ed. MIT Press.