RL-PGO: Reinforcement Learning-Based Planar Pose-Graph Optimization.
Nikolaos KourtzanidisSajad Saeedi G.Published in: IEEE Control. Syst. Lett. (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- markov decision processes
- reinforcement learning algorithms
- temporal difference
- partially observable domains
- directed graph
- optimization algorithm
- supervised learning
- learning process
- multi agent
- random walk
- optimization problems
- graph structure
- action selection
- model free
- learning algorithm
- machine learning
- optimal policy
- pose estimation
- d objects
- planar graphs
- temporal difference learning
- transfer learning
- learning problems
- ground plane
- graph matching
- partially observable
- markov decision process
- policy iteration
- control policy
- optimal control
- continuous state
- graph theory