Relocatable Action Models for Autonomous Navigation
Bethany R. Leer, Michael L. Littman · 2007
A reinforcement-learning agent, in general, uses information from the environment to determine the value of its actions. Once the agent begins acting in the world, there is no further modification of its behavior by humans. This lack of human control makes the use of reinforcement learning a natural solution to the autonomous navigation and exploration problem. However, implementing algorithms from this field has not always been possible in the robotic domain.