Curious Meta-Controller: Adaptive Alternation between Model-Based and Model-Free Control in Deep Reinforcement Learning.
Muhammad Burhan HafezCornelius WeberMatthias KerzelStefan WermterPublished in: CoRR (2019)
Keyphrases
- model free
- impedance control
- reinforcement learning
- adaptive control
- reinforcement learning algorithms
- optimal control
- function approximation
- temporal difference
- control system
- control policy
- control method
- adaptive neural
- control strategies
- visual servoing
- state space
- control architecture
- policy evaluation
- control strategy
- learning algorithm
- robotic manipulator
- policy iteration
- actor critic
- optimal policy
- markov decision processes
- traffic signal
- machine learning
- reinforcement learning methods
- dynamic programming
- supervised learning
- robotic systems
- learning problems
- transfer learning
- rl algorithms
- data mining
- robot control
- fuzzy logic controller
- feature selection
- neural network
- learning tasks