Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning
Sheng Li,Yutai Zhou,Ross Allen,Mykel J. Kochenderfer,Sheng Li,Yutai Zhou,Ross Allen,Mykel J. Kochenderfer
Communication is an important factor that en-ables agents to work cooperatively in multi-agent reinforcement learning (MARL) contexts. Prior work used continuous message communication whose high representational capacity comes at the expense of interpretability. Allowing agents to learn their own discrete emergent message communication protocols can increase the interpretability for human designer...
