An overview of the proposed model (IMAGE)
Caption
During the training process, the paper uses inner-agent and inter-agent contrastive representation learning objectives (left) to train the consensus inference models for developing DuCC. In the inference process, it uses consensus inference models (middle) to abstract consensus representations from local observations, and consensus representation-augmented decentralized
policies (right) to select coordinated actions.
Credit
Beijing Zhongke Journal Publising Co. Ltd.
Usage Restrictions
Credit must be given to the creator.
License
CC BY