Skip to content

A
AAAI21_Emergent_language
Commit 7a3fbf89 by Zidong Du
Options

~

parent 75a40a38
Showing with 4 additions and 3 deletions
NIPS2020/main.tex
...@@ -168,9 +168,10 @@ systems. However, even using the multi-agent systems, previous works at root are ...@@ -168,9 +168,10 @@ systems. However, even using the multi-agent systems, previous works at root are
training one brain for communicating among connected sensors (agents), as they combine training one brain for communicating among connected sensors (agents), as they combine
the neural networks of all agents in the training process. the neural networks of all agents in the training process.
Roughly, previous works force the agents evolving for generating communication Roughly, to evolve a symbolic language, previous works force the
protocol by setting a target that requires the cooperation of multiple agents to finish a set target through cooperation, which requires communication
agents. These works can be classified into two categories based on the among the agents.
These works can be classified into two categories based on the
environment settings: \emph{referential games} and \emph{multi-agent environment settings: \emph{referential games} and \emph{multi-agent
reinforcement learning system}. reinforcement learning system}.
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment