PILCO is a model-based Reinforcement Learning method introduced in 2011 by Deisenroth and Rasmussen. As far as I know, it is still considered one of the most important RL method, especially for its impressive sample efficiency. The original paper has (at the time of writing) 444 certified citation on Scopus, and more than 1000 on Google Scholar.

Nevertheless, PILCO has not been included in the second edition of "Reinforcement Learning. An Introduction" by Sutton and Barto (2018).

Could you explain why? My thought is that Sutton-Barto monograph is devoted only to MDP, while PILCO setting is slightly more general, considering both continuous state-space and continuous action-space.


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.