Login / Signup
The True Online Continuous Learning Automation (TOCLA) in a continuous control benchmarking of actor-critic algorithms.
Gordon Frost
Marta Vallejo
Published in:
SSCI (2020)
Keyphrases
</>
learning algorithm
actor critic
reinforcement learning
learning problems
optimal control
policy gradient methods
supervised learning
control strategy
active learning
learning tasks
reinforcement learning methods
control system
control strategies
policy iteration