Cascaded Attention: Adaptive and Gated Graph Attention Network for Multiagent Reinforcement Learning
Abstract: Modeling the interactive relationships of agents is critical to improving the collaborative capability of a multiagent system. Some methods model these by predefined rules. However, due to ...
Abstract: Convolutional networks have enjoyed much success in many computer vision applications. The convolution operation however has a significant weakness in that it only operates on a local ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results