From self-tuning regulators to reinforcement learning and back again.
Nikolai MatniAlexandre ProutièreAnders RantzerStephen TuPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- state space
- markov decision processes
- model free
- reinforcement learning algorithms
- learning algorithm
- multi agent
- control problems
- real time
- temporal difference learning
- temporal difference
- dynamic programming
- robot control
- direct policy search
- database
- action selection
- transfer learning
- least squares
- learning process
- neural network