Learning Options for an MDP from Demonstrations
- Cite this paper as:
- Tamassia M., Zambetta F., Raffe W., Li X. (2015) Learning Options for an MDP from Demonstrations. In: Chalup S.K., Blair A.D., Randall M. (eds) Artificial Life and Computational Intelligence. ACALCI 2015. Lecture Notes in Computer Science, vol 8955. Springer, Cham
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.
Keywordsreinforcement learning options
Unable to display preview. Download preview PDF.