Robust and Efficient Transfer Learning with Hidden-Parameter Markov Decision Processes
This work provides a more robust and efficient transfer learning method for reinforcement learning applications, though it appears incremental as it builds upon the existing HiP-MDP framework.
The authors tackled the problem of modeling families of related tasks in reinforcement learning by introducing a new formulation of the Hidden Parameter Markov Decision Process (HiP-MDP) that correctly models joint uncertainty and uses Bayesian Neural Networks for scalability, enabling applications with higher dimensions and more complex dynamics.
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.