Joint Policy Search for Multi-agent Collaboration with Imperfect Information.

Yuandong Tian Qucheng Gong Yu Jiang

Published in: NeurIPS (2020)

Keyphrases

imperfect information
policy search
game theoretic
game playing
reinforcement learning
continuous state
imperfect information games
game theory
reinforcement learning algorithms
dynamic programming
nash equilibrium
finite automata
cooperative
resource allocation
game tree
policy gradient