Login / Signup
Compulsory Flow Q-Learning: an RL algorithm for robot navigation based on partial-policy and macro-states.
Valdinei Freire da Silva
Anna Helena Reali Costa
Published in:
J. Braz. Comput. Soc. (2009)
Keyphrases
</>
robot navigation
learning algorithm
reinforcement learning
optimal policy
rl algorithms
dynamic programming
path planning
temporal difference learning
machine learning
object recognition
multi view
expectation maximization