Graph convolution with topology refinement for Automatic Reinforcement Learning.
Jianghui SangYongli WangPublished in: Neurocomputing (2023)
Keyphrases
- reinforcement learning
- function approximation
- small world
- graph structure
- semi automatic
- graph model
- image processing
- random walk
- graph representation
- connected components
- learning algorithm
- fully automatic
- convolution kernel
- reinforcement learning algorithms
- graph theoretic
- graph mining
- graph theory
- optimal policy
- multi agent
- weighted graph
- spanning tree
- structured data
- state space
- pairwise
- function approximators
- fully connected