Kernel-based diffusion approximated Markov decision processes for autonomous navigation and control on unstructured terrains.
Junhong XuKai YinZheng ChenJason M. GregoryEthan A. StumpLantao LiuPublished in: Int. J. Robotics Res. (2024)
Keyphrases
- markov decision processes
- autonomous navigation
- motion control
- finite state
- mobile robot
- optimal policy
- reinforcement learning
- transition matrices
- dynamic environments
- decision theoretic planning
- dynamic programming
- state space
- reachability analysis
- policy iteration
- average cost
- average reward
- infinite horizon
- partially observable
- path planning
- action sets
- model based reinforcement learning
- planning under uncertainty
- optimal control
- ego motion
- action space
- computer vision
- optimal solution
- markov decision process
- reward function
- linear program
- least squares