Login / Signup
A study on hierarchical modular reinforcement learning for multi-agent pursuit problem based on relative coordinate states.
Tatsuya Wada
Takuya Okawa
Toshihiko Watanabe
Published in:
CIRA (2009)
Keyphrases
</>
multi agent
reinforcement learning
cooperative
multi agent systems
real time
machine learning
statistical analysis
multiagent systems
simulation study
dynamic programming
state space
empirical studies
function approximation
learning agents
modular structure