Title | ||
---|---|---|
Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes. |
Abstract | ||
---|---|---|
An intriguing application of transfer learning emerges when tasks arise with similar, but not identical, dynamics. Hidden Parameter Markov Decision Processes (HiP-MDP) embed these tasks into a low-dimensional space; given the embedding parameters one can identify the MDP for a particular task. However, the original formulation of HiP-MDP had a critical flaw: the embedding uncertainty was modeled independently of the agent's state uncertainty, requiring an arduous training procedure. In this work, we apply a Gaussian Process latent variable model to jointly model the dynamics and the embedding, leading to a more elegant formulation, one that allows for better uncertainty quantification and thus more robust transfer. |
Year | Venue | DocType |
---|---|---|
2017 | THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE | Conference |
Citations | PageRank | References |
1 | 0.37 | 20 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Taylor Killian | 1 | 1 | 3.75 |
George Konidaris | 2 | 801 | 59.30 |
finale doshivelez | 3 | 574 | 51.99 |