Timezone: »

 
Poster
Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes
Taylor Killian · Samuel Daulton · Finale Doshi-Velez · George Konidaris

Wed Dec 06 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #36
in Posters Wed »

We introduce a new formulation of the Hidden Parameter Markov Decision Process (HiP-MDP), a framework for modeling families of related tasks using low-dimensional latent embeddings. Our new framework correctly models the joint uncertainty in the latent parameters and the state space. We also replace the original Gaussian Process-based model with a Bayesian Neural Network, enabling more scalable inference. Thus, we expand the scope of the HiP-MDP to applications with higher dimensions and more complex dynamics.

Keywords: Multitask and Transfer Learning · Reinforcement Learning and Planning · Latent Variable Models · Reinforcement Learning · Model-Based RL · Markov Decision Processes
[ Code]  [ Paper] 

Author Information

Taylor Killian (Harvard University)
Samuel Daulton (Facebook)

Research Scientist at Meta, PhD Candidate at Oxford. My research focuses on Bayesian optimization.

Finale Doshi-Velez (Harvard)
George Konidaris (Brown University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors