Scalable and transferable learning of algorithms via graph embedding for multi-robot reward collection.
Hyunwook KangAydar MynbayJames R. MorrisonJinkyoo ParkPublished in: CoRR (2019)
Keyphrases
- learning algorithm
- multi robot
- graph embedding
- multi robot exploration
- learning process
- reinforcement learning
- mobile robot
- prior knowledge
- unsupervised learning
- initially unknown
- machine learning
- training set
- support vector machine
- image classification
- gaussian mixture model
- path planning
- data representation
- computer vision