When the transition probabilities and rewards of a Markov Decision Process are specified exactly, the problem can be solved without any interaction with the environment. When no s...
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
Alexander L. Strehl, Lihong Li, Eric Wiewiora, Joh...
How should a reinforcement learning agent act if its sole purpose is to efficiently learn an optimal policy for later use? In other words, how should it explore, to be able to exp...
Partially Observable Markov Decision Process models (POMDPs) have been applied to low-level robot control. We show how to use POMDPs differently, namely for sensorplanning in the ...
Cross-layer optimization aims at improving the performance of network users operating in a time-varying, error-prone wireless environment. However, current solutions often rely on...