Repository | Book | Chapter
(2015) Artificial life and computational intelligence, Dordrecht, Springer.
Learning options for an mdp from demonstrations
Marco Tamassia , Fabio Zambetta , William Raffe , Xiaodong Li
pp. 226-242
The options framework provides a foundation to use hierarchical actions in reinforcement learning. An agent using options, along with primitive actions, at any point in time can decide to perform a macro-action made out of many primitive actions rather than a primitive action. Such macro-actions can be hand-crafted or learned. There has been previous work on learning them by exploring the environment. Here we take a different perspective and present an approach to learn options from a set of experts demonstrations. Empirical results are also presented in a similar setting to the one used in other works in this area.
Publication details
DOI: 10.1007/978-3-319-14803-8_18
Full citation:
Tamassia, M. , Zambetta, F. , Raffe, W. , Li, X. (2015)., Learning options for an mdp from demonstrations, in M. Randall (ed.), Artificial life and computational intelligence, Dordrecht, Springer, pp. 226-242.
This document is unfortunately not available for download at the moment.