Improving RL power for on-line evolution of gaits in modular robots.

Milan Jelisavcic Matteo De Carlo Evert Haasdijk A. E. Eiben

Published in: SSCI (2016)

Keyphrases

modular robots
reinforcement learning
learning agents
robotic systems
distributed systems
real time
optimal policy
function approximation
model free
neural network
multi agent
evolutionary algorithm
state space
changing environment
robot behavior