Login / Signup
Using a Time-Delay Actor-Critic Neural Architecture with Dopamine-Like Reinforcement Signal for Learning in Autonomous Robots.
Andrés Pérez-Uribe
Published in:
Emergent Neural Computational Architectures Based on Neuroscience (2001)
Keyphrases
</>
autonomous robots
reinforcement learning
actor critic
neural architecture
learning algorithm
mobile robot
learning problems
optimal control
supervised learning
temporal difference
machine learning
active learning
state space
non stationary
learning tasks