RL-PGO: Reinforcement Learning-based Planar Pose-Graph Optimization.
Nikolaos KourtzanidisSajad SaeediPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- temporal difference
- optimization problems
- model free
- optimal policy
- markov decision processes
- planar graphs
- autonomous learning
- pose estimation
- graph matching
- direct policy search
- action selection
- machine learning
- learning algorithm
- transfer learning
- optimization algorithm
- random walk
- graph structure
- learning process
- temporal difference learning
- learning problems
- partially observable domains
- min sum
- d objects
- partially observable
- multi agent
- genetic algorithm
- policy search
- policy gradient
- reinforcement learning methods
- control policy
- evolutionary algorithm
- dynamic programming
- position and orientation
- optimal control
- directed graph