Reinforcement Planning: RL for optimal planners

@article{Zucker2012ReinforcementPR,
  title={Reinforcement Planning: RL for optimal planners},
  author={Matthew Zucker and J. Andrew Bagnell},
  journal={2012 IEEE International Conference on Robotics and Automation},
  year={2012},
  pages={1850-1855}
}
Search based planners such as A* and Dijkstra's algorithm are proven methods for guiding today's robotic systems. Although such planners are typically based upon a coarse approximation of reality, they are nonetheless valuable due to their ability to reason about the future, and to generalize to previously unseen scenarios. However, encoding the desired behavior of a system into the underlying cost function used by the planner can be a tedious and error-prone task. We introduce Reinforcement… CONTINUE READING