M. Geist
YOU?
Author Swipe
View article: Periodic agent-state based Q-learning for POMDPs
Periodic agent-state based Q-learning for POMDPs Open
The standard approach for Partially Observable Markov Decision Processes (POMDPs) is to convert them to a fully observed belief-state MDP. However, the belief state depends on the system model and is therefore not viable in reinforcement l…