Direct Policy Transfer via Hidden Parameter Markov Decision Processes

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Reinforcement Learning in Healthcare: A Survey (2019, background): “take advantage of the prior information from previously learned transition models [106, 107] or learned policies [243].”
Generalized Hidden Parameter MDPs Transferable Model-based RL in a Handful of Trials (2020, background): “Recent prior work on latent variable models of MDPs focused on models of dynamics with small discrete action spaces (Doshi-Velez and Konidaris 2016; Killian et al. 2017; Yao et al. 2018).”
Fast Adaptation to New Environments via Policy-Dynamics Value Functions (2020, methodology): “Yao et al. (2018) uses a fully-trained BNN to further optimize latent variables during a single test episode, but requires an optimal policy for each training instance, which makes it harder to scale.”
VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning (2019, result): “…of hidden parameter (HiP-) MDPs assumes that there is a set of low-dimensional latent factors which define a family of related dynamical systems (with shared reward structure), similar to the assumption we make in Equation (5) (Doshi-Velez & Konidaris, 2016; Killian et al., 2017; Yao et al., 2018).”