Source code (2-agent grid world) for the journal paper "Multiagent Reinforcement Learning With Sparse Interactions by Negotiation and Knowledge Transfer", which is an English version of my undergrad thesis at Nanjing University. Please refer to the following paper for more details

• Multiagent Reinforcement Learning With Sparse Interactions by Negotiation and Knowledge Transfer, L. Zhou et al., IEEE Transactions on Cybernetics 2017.

and cite the following if you find the code useful.

@article{zhou2017multiagent,
  title={Multiagent reinforcement learning with sparse interactions by negotiation and knowledge transfer},
  author={Zhou, Luowei and Yang, Pei and Chen, Chunlin and Gao, Yang},
  journal={IEEE transactions on cybernetics},
  volume={47},
  number={5},
  pages={1238--1250},
  year={2017},
  publisher={IEEE}
}