Solving Bellman Equations in a Stochastic Shortest Path Problem of Package Delivery

Package Delivery World


The objective of the project is to deliver a package with a drone as quickly as possible. To achieve this, the drone must first fly to a pick-up station to collect a package and then reach a delivery station to discharge it. Along the way, the drone must avoid hazards such as trees or angry residents who try to shoot it down. In this project, the optimal policy minimizing the expected number of time steps required to successfully deliver a package is obtained by using value iteration, policy iteration and linear programming algorithms in a discrete infinite horizon setting.

Chenhao Li
Chenhao Li
Reinforcement Learning for Robotics

My research interests focus on the general field of robot learning, including reinforcement learning, developmental robotics and legged intelligence.