Revisiting the Gumbel-Softmax in MADDPG.
Callum Rhys TilburyFilippos ChristianosStefano V. AlbrechtPublished in: CoRR (2023)
Keyphrases
- activation function
- temporal difference learning
- multiscale
- multiresolution
- search space
- data sets
- artificial intelligence
- data analysis
- reinforcement learning
- data mining
- multi class
- control system
- pattern recognition
- search algorithm
- multi agent
- image segmentation
- decision trees
- learning algorithm
- learning environment
- bayesian networks
- feature extraction
- learning process
- knowledge base
- active learning
- computer vision
- dynamic programming
- social networks
- fuzzy logic
- input image
- machine learning