Agents
b39fcf2e88dad4c38386b3af6edf88c7-Paper-Conference.pdf
We propose to view the outcomes of the agents' dynamics as inducing a "meta-game" between the users.
Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction
Alban Laflaquière, Michael Garcia Ortiz
Neural Information Processing Systems http://nips.cc/
LIIR: Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning
Yali Du, Lei Han, Meng Fang, Ji Liu, Tianhong Dai, Dacheng Tao
Without a centralized controller, each agent is responsible to collaborate with others on its own decision.
