Login / Signup
Large-scale cost function learning for path planning using deep inverse reinforcement learning.
Markus Wulfmeier
Dushyant Rao
Dominic Zeng Wang
Peter Ondruska
Ingmar Posner
Published in:
Int. J. Robotics Res. (2017)
Keyphrases
</>
path planning
cost function
inverse reinforcement learning
mobile robot
robot path planning
dynamic environments
path planning algorithm
collision avoidance
learning algorithm
obstacle avoidance
reinforcement learning
learning tasks
multi robot
markov chain
preference elicitation
partially observable environments