Message-Dropout: An Efficient Training Method for Multi-Agent Deep Reinforcement Learning.
Woojun KimMyungsik ChoYoungchul SungPublished in: AAAI (2019)
Keyphrases
- multi agent
- reinforcement learning
- detection method
- experimental evaluation
- segmentation method
- synthetic data
- training phase
- computationally efficient
- support vector machine svm
- cost function
- high accuracy
- classification method
- high precision
- training algorithm
- training samples
- support vector machine
- feature set
- edge detection
- data sets
- state space
- probabilistic model
- computational cost
- significant improvement
- k means
- cooperative
- objective function
- genetic algorithm
- machine learning