Login / Signup
An actor-critic approach for learning cooperative behaviors of multiagent seesaw balancing problems.
Takashi Kawakami
Masahiro Kinoshita
Michiko Watanabe
Norihiko Takatori
Masashi Furukawa
Published in:
SMC (2005)
Keyphrases
</>
cooperative
multi agent
actor critic
reinforcement learning
learning algorithm
learning tasks
solving problems
supervised learning
optimization problems
machine learning
optimal solution
dynamical systems
game theory
kernel methods
adaptive control
temporal difference