Safe Q-Learning on Complete History Spaces

In this article, we present an idea for solving deterministic partially observable markov decision processes (POMDPs) based on a history space containing sequences of past observations and actions. A novel and sound technique for learning a Q-function on history spaces is developed and discussed. We analyze certain conditions under which a history based approach is able to learn policies comparable to the optimal solution on belief states. The algorithm presented is model-free and can be combined with any method learning history spaces. We also present a procedure able to learn history spaces especially suited for our Q-learning algorithm.

• Type: Conference
• Year: 2007
• Where: ECML
• Authors: Stephan Timmer, Martin Riedmiller
• Keywords: ECML 2007, History Spaces, Machine Learning, Observable Markov Decision, Space Containing Sequences